はてなキーワード: Actionとは
お前のいう通り書いたったわ(C#だが)。
//宇宙 namespace Universe { //あらゆる神の根底に存在する唯一神とその司る運(スーパークラス) public class GodLuck { public string Name { get; } //神の名前 public string Power { get; } //神の力 public string Plan { get; } //神の計画 public string Factor { get; } //運の要因 public GodLuck(string name, string power, string plan, string factor) { Name = name; //神の名前 Power = power; //神の力 Plan = plan; //神の計画 Factor = factor; //運の要因 } //神が何かを創造するメソッド public void Create(string thing) { Console.WriteLine($"{Name} created {thing}."); } //神が何かに対して支配や介入をするメソッド public void Control(string thing, string action) { Console.WriteLine($"{Name} {action} {thing}."); } //運が何かに対して影響を与えるメソッド public void Affect(string thing, string outcome) { Console.WriteLine($"{Name} affected {thing} and the outcome was {outcome}."); } } //恵比須様 public class EbisuSama : GodLuck { public EbisuSama() : base("恵比須様", "商売繁盛や五穀豊穣の力", "人々に幸せを与える計画", "商売繁盛や五穀豊穣の要因") { } //作物を守る public void Save(string crops) { Control(crops, "守る"); } //人間を成功させる public void MakeSuccessful(string person) { Affect(person, "成功"); } } }
(大いなる力を別のクラスに移譲したくなったが、神と大いなる力は同一のオブジェクトという要件があるからやめた)
//宇宙 namespace Universe { //神の振る舞いを定義したインターフェイス public interface IGodLuck { public string Name { get; } public string Power { get; } public string Plan { get; } public string Factor { get; } //神が何かを創造するメソッド public void Create(string thing); //神が何かに対して支配や介入をするメソッド public void Control(string thing, string action); //運が何かに対して影響を与えるメソッド public void Affect(string thing, string outcome); } //恵比須様 public class EbisuSama : IGodLuck { public string Name { get; } //神の名前 public string Power { get; } //神の力 public string Plan { get; } //神の計画 public string Factor { get; } //運の要因 public EbisuSama() { Name = "恵比須様"; //神の名前 Power = "商売繁盛や五穀豊穣の力"; //神の力 Plan = "人々に幸せを与える計画"; //神の計画 Factor = "商売繁盛や五穀豊穣の要因"; //運の要因 } //神が何かを創造するメソッド public void Create(string thing) { Console.WriteLine($"{Name} created {thing}."); } //神が何かに対して支配や介入をするメソッド public void Control(string thing, string action) { Console.WriteLine($"{Name} {action} {thing}."); } //運が何かに対して影響を与えるメソッド public void Affect(string thing, string outcome) { Console.WriteLine($"{Name} affected {thing} and the outcome was {outcome}."); } //物を守る public void Save(string thing) { Control(thing, "守る"); } //人間を成功させる public void MakeSuccessful(string person) { Affect(person, "成功"); } } }
万物に神が宿り、万物が神になる世界なので、神が人や世界を支配しない
『西洋宗教において神と運は別のオブジェクトだが、日本の古典な宗教観においては神や大いなる力は同一のオブジェクト』、これを生成させるまではうまくいったんだけどね
bingちゃん:
西洋宗教では、神と運は、プログラムでたとえると、別々のオブジェクトとして存在すると考えられます。神は、人間や自然に対して意志や計画を持つ創造者や支配者として表現されます。運は、人間や自然に対して予測や制御ができない偶発的な要因として表現されます。
# 神と運のオブジェクトを定義する class God: def __init__(self, name, power, plan): self.name = name # 神の名前 self.power = power # 神の力 self.plan = plan # 神の計画 def create(self, thing): # 神が何かを創造するメソッド print(f"{self.name} created {thing}.") def control(self, thing, action): # 神が何かに対して支配や介入をするメソッド print(f"{self.name} {action} {thing}.") class Luck: def __init__(self, name, factor): self.name = name # 運の名前 self.factor = factor # 運の要因 def affect(self, thing, outcome): # 運が何かに対して影響を与えるメソッド print(f"{self.name} affected {thing} and the outcome was {outcome}.")このコードでは、神と運は、それぞれ異なる属性や機能を持つオブジェクトとして定義されています。神は、名前、力、計画という属性と、創造、支配という機能を持ちます。運は、名前、要因という属性と、影響という機能を持ちます。神と運は、それぞれの機能を使って、人間や自然に対して作用することができます。例えば、以下のようなコードが考えられます。
# 神と運のオブジェクトを作成する god = God("Zeus", "lightning", "maintain order") luck = Luck("Tyche", "chance") # 神と運が人間に対して作用する god.create("human") luck.affect("human", "good") god.control("human", "bless") luck.affect("human", "bad") god.control("human", "punish")しかし、日本の古典的宗教観では運と神や大いなる力は同じオブジェクトです。神が運を司っています。
# 神と運は同一のオブジェクトとして定義する class GodLuck: def __init__(self, name, power, plan, factor): self.name = name # 神の名前 self.power = power # 神の力 self.plan = plan # 神の計画 self.factor = factor # 運の要因 def create(self, thing): # 神が何かを創造するメソッド print(f"{self.name} created {thing}.") def control(self, thing, action): # 神が何かに対して支配や介入をするメソッド print(f"{self.name} {action} {thing}.") def affect(self, thing, outcome): # 運が何かに対して影響を与えるメソッド print(f"{self.name} affected {thing} and the outcome was {outcome}.")このように、神と運は同一のオブジェクトとして扱われます。例えば、恵比寿さまは商売繁盛や五穀豊穣の神であり、同時にそのような運をもたらす要因でもあります。以下がその例です。
# 恵比寿さまのオブジェクトを作る ebisu = GodLuck("恵比寿さま", "商売繁盛や五穀豊穣の力", "人々に幸せを与える計画", "商売繁盛や五穀豊穣の要因") # 恵比寿さまが何かを創造する ebisu.create("鯛") # 恵比寿さまが何かに対して支配や介入をする ebisu.control("農作物", "守る") # 恵比寿さまが何かに対して影響を与える ebisu.affect("商人", "成功")恵比寿さま created 鯛. 恵比寿さま 守る 農作物. 恵比寿さま affected 商人 and the outcome was 成功.
日本語で聞いてるのになんでその回答になるんだよ、面倒くせぇ
ぜんぜん中立じゃないじゃんな
具体的にはBingちゃんが神の計画・神の支配の文言含んだ回答を生成しちゃったら
日本は八百万の神がいる世界。万物に神が宿り、万物が神になる世界なので、神が人や世界を支配しない
『西洋宗教において神と運は別のオブジェクトだが、日本の古典な宗教観においては神や大いなる力は同一のオブジェクト』、これをBingちゃんに生成させるまではうまくいったんだけどね
bingちゃん:
西洋宗教では、神と運は、プログラムでたとえると、別々のオブジェクトとして存在すると考えられます。神は、人間や自然に対して意志や計画を持つ創造者や支配者として表現されます。運は、人間や自然に対して予測や制御ができない偶発的な要因として表現されます。
# 神と運のオブジェクトを定義する class God: def __init__(self, name, power, plan): self.name = name # 神の名前 self.power = power # 神の力 self.plan = plan # 神の計画 def create(self, thing): # 神が何かを創造するメソッド print(f"{self.name} created {thing}.") def control(self, thing, action): # 神が何かに対して支配や介入をするメソッド print(f"{self.name} {action} {thing}.") class Luck: def __init__(self, name, factor): self.name = name # 運の名前 self.factor = factor # 運の要因 def affect(self, thing, outcome): # 運が何かに対して影響を与えるメソッド print(f"{self.name} affected {thing} and the outcome was {outcome}.")このコードでは、神と運は、それぞれ異なる属性や機能を持つオブジェクトとして定義されています。神は、名前、力、計画という属性と、創造、支配という機能を持ちます。運は、名前、要因という属性と、影響という機能を持ちます。神と運は、それぞれの機能を使って、人間や自然に対して作用することができます。例えば、以下のようなコードが考えられます。
# 神と運のオブジェクトを作成する god = God("Zeus", "lightning", "maintain order") luck = Luck("Tyche", "chance") # 神と運が人間に対して作用する god.create("human") luck.affect("human", "good") god.control("human", "bless") luck.affect("human", "bad") god.control("human", "punish")しかし、日本の古典的宗教観では運と神や大いなる力は同じオブジェクトです。神が運を司っています。
# 神と運は同一のオブジェクトとして定義する class GodLuck: def __init__(self, name, power, plan, factor): self.name = name # 神の名前 self.power = power # 神の力 self.plan = plan # 神の計画 self.factor = factor # 運の要因 def create(self, thing): # 神が何かを創造するメソッド print(f"{self.name} created {thing}.") def control(self, thing, action): # 神が何かに対して支配や介入をするメソッド print(f"{self.name} {action} {thing}.") def affect(self, thing, outcome): # 運が何かに対して影響を与えるメソッド print(f"{self.name} affected {thing} and the outcome was {outcome}.")このように、神と運は同一のオブジェクトとして扱われます。例えば、恵比寿さまは商売繁盛や五穀豊穣の神であり、同時にそのような運をもたらす要因でもあります。以下がその例です。
# 恵比寿さまのオブジェクトを作る ebisu = GodLuck("恵比寿さま", "商売繁盛や五穀豊穣の力", "人々に幸せを与える計画", "商売繁盛や五穀豊穣の要因") # 恵比寿さまが何かを創造する ebisu.create("鯛") # 恵比寿さまが何かに対して支配や介入をする ebisu.control("農作物", "守る") # 恵比寿さまが何かに対して影響を与える ebisu.affect("商人", "成功")恵比寿さま created 鯛. 恵比寿さま 守る 農作物. 恵比寿さま affected 商人 and the outcome was 成功.
そんなことより臭っせえ犯罪者集団暇アノンの自作自演を見てくれよ!!!
https://anond.hatelabo.jp/20231114213423
60.57.58.164の投稿記録 https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/60.57.58.164
58.70.26.54の投稿記録 https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/58.70.26.54
180.148.3.230の投稿記録 https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/180.148.3.230
Konnnitihaseizinnnosabuの投稿記録 https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/Konnnitihaseizinnnosabu
くせえええええ!!!!
60.57.58.164の投稿記録
https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/60.57.58.164
58.70.26.54の投稿記録
https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/58.70.26.54
180.148.3.230の投稿記録
https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E6%8A%95%E7%A8%BF%E8%A8%98%E9%8C%B2/180.148.3.230
this is completely false for AWD cars, I don't get why it gets repeated so much.
Ideally you want all 4 wheels to have the same amount of weight over them in an AWD launch, this way each wheel puts power down optimally. Since weight shifts towards the back during acceleration, this means that the ideal weight distribution for launching is somewhat to the front.
The RS3 is a good example of this effect in action, it launches well despite having a meh Haldex-like AWD system. The Hellcat on a prepped surface is another, despite being RWD.
Since the Turbo S is the opposite, it compensates by having way wider rear tyres compared to the front ones (255 front, 315 rear).
So actually the 911 launches well DESPITE the fact that it's rear-heavy, not because of it. It just modulates its power way better than the competition.
The 911's setup instead makes it brake so well, since the same principle as above applies just in the opposite direction.
「これはAWD車にとっては完全に間違いだ。なぜこのような誤解が繰り返されるのか理解できない。
AWDの発進では、4輪すべてに同じ重さがかかるのが理想的で、そうすることで各輪が最適にパワーを発揮する。加速時に重量が後ろに移動するため、発進時の理想的な重量配分はややフロント寄りになる。
RS3はこの効果の良い例で、ハルデックスのようなAWDシステムを搭載しているにもかかわらず、うまく発進する。整地された路面でのヘルキャットも、FRにもかかわらずそうだ。
ターボSはその逆であるため、フロントタイヤに比べてリアタイヤをかなりワイド(フロント255、リア315)にすることで埋め合わせをしている。
つまり、911はリアヘビー「であるにもかかわらず」発進がいいのであって、リアヘビーだから発進がいいのではない。911は競争相手よりもパワーをはるかにうまく伝えている。
はじめは外国の方のプレイ動画なのかと思い、珍しいなと思って見てたら、プレイする様子がなく、
題に「reviews」が入っていて、長さが6時間なのに驚いた
104万回再生されているけど、6時間のゲームレビュー動画をそんなに見るものなのか?
コメントにも「6時間もどうやってゲームレビューするんだ?と思ってた。見終わったらもう6時間くらいレビューしてくれと思っている自分がいる」みたいなコメントついている
そんなに何を話しているんだろうと思って、4時間目くらいを見てみたら、小学校らしき教室が映っていた
このレビュワー、自分のノスタルジーについて説明するために母校に行っているのだろうか
3/25
ttps://twitter.com/nhk_sports/status/1639609183485198336
4/5
ttps://www3.nhk.or.jp/sapporo-news/20230405/7000056515.html
4/11〜16(一番奥?)
ttps://thegrandslamofcurling.com/wp-content/uploads/25-yoshida-1024x683.jpeg
5/2~7
ttps://thegrandslamofcurling.com/wp-content/uploads/2023ChampionsCup-ReginaSK-action-079-1024x576.jpg
ttps://twitter.com/grandslamcurl/status/1654996887995314176
https://ameblo.jp/loco-log/entry-12803106138.html
ttps://ameblo.jp/loco-log/entry-12808667952.html
ttps://ameblo.jp/loco-log/entry-12810102603.html
ttps://locosolare.jp/news/info/20230604_bs-tbs-kokorolab/
6/5
https://kyodonewsprwire.jp/release/202306066174
7/14
https://www.joc.or.jp/news/detail.html?id=16056
シーズン終了後のスポンサー企業への挨拶回りの時点で顔の脂肪が落ちはじめてるのがわかる。
6/5の時点でだいぶ顔が痩せているが、1ヶ月足らずでこんなに変われるってすごくない?
ここ1年で初めてはてなブックマーク日毎の総合人気エントリ入りしたドメインからのホットエントリ、ブクマ数順トップ30
ブクマ数 | タイトル | ドメイン |
---|---|---|
1960 | 引越しにおけるネット回線ガチャと開通待ちで勝利するための知見まとめ 2023春 - はげあたま.org | www.hageatama.org |
1948 | 仕事力チェックリスト50 ~「会議の進め方」から「タスク管理の方法」まで~|株式会社才流 | sairu.co.jp |
1145 | 総務省統計局 データサイエンス・オンライン講座 社会人のためのデータサイエンス入門 | gacco.org |
1059 | ジャニー喜多川 - ジャニーズ百科事典 | jjpedia.web.fc2.com |
967 | アンチマン / アンチマン - 岡田索雲 | webアクション | comic-action.com |
956 | 米軍式睡眠法とは やり方と効果を高めるASMRを紹介 | www.asmrmedia.net |
892 | CityHop | www.cityhop.cafe |
802 | あのエロい映画なんだっけ? / あのエロい映画なんだっけ? - 鈴木健也 | webアクション | comic-action.com |
781 | パワポ資料で「つい、やってしまう失敗」から学ぶ!ガチ改善テクニック14選 | tomoyukiarasuna.com |
740 | 女性ソロキャンパーへ話しかけに行く男性について日本単独野営協会が思うこと – ソロキャンプ ー日本単独野営協会 公式サイト ー | tandokuyaei.com |
711 | 伝わりやすいスライド資料の作り方。資料作成の流れからデザインのコツ、デザイン初心者さんにおすすめの本まで紹介|fuyuna blog|デザイン・ライフスタイル・キャリアについて書くデザイナーのブログ | fuyuna.net |
685 | 県営公園での過激な「水着撮影会」の貸出中止を埼玉県に求める | 日本共産党埼玉県議会議員団 | www.jcp-saitama-pref.jp |
660 | 他人がSNS中傷を「捏造」、木村花さんの母は気づかず提訴…真偽見極め困難 | www.yomiuri.co.jp |
630 | 【全公開】落合陽一も絶賛、GPT「究極のプロンプト」 | newspicks.com |
612 | デジタル庁のデータ分析基盤「sukuna」|デジタル庁 | digital-gov.note.jp |
588 | 使い込んだフライパンでも綺麗に焼けるギョーザの検証に向けたお願い | 味の素冷凍食品株式会社 | www.ffa.ajinomoto.com |
577 | サッカーは帰納法 | ashiki-feelings.blogspot.com |
574 | 撮り鉄の高校生、非常停止ボタンを踏切6か所で押す「好きなアングルで撮りたかった」 | www.yomiuri.co.jp |
562 | プレイ可能な状態での「過去のゲームの合法的保存」について - 赤松健 - 公式サイト | kenakamatsu.jp |
539 | 9か月勾留「野菜不足の弁当」で40代男性が一時危篤、ビタミン不足で脚気と診断 : 読売新聞 | www.yomiuri.co.jp |
537 | VOL.22自分は水着にならないと価値がないと思っている女の子へ | ishikawa-yumi.theletter.jp |
532 | どなたでも利用できる、イラストレーション・アイコン素材集を配布します |デジタル庁 | digital-gov.note.jp |
518 | 北大祭2023 小泉悠さんがロシア・ウクライナ戦争を講演 | costep.open-ed.hokudai.ac.jp |
510 | 任天堂株主総会レポート2023 | n-styles.com |
504 | 物流は本当に付加価値がない業務なのか | タイム・コンサルタントの日誌から | brevis.exblog.jp |
497 | クックパッドが人員削減の合理化と営業損失計上を発表 対象人員数は110名 : 官報ブログ | kanpo-kanpo.blog.jp |
491 | スシロー迷惑動画、しょうゆ差しなめた少年を提訴…6700万円損賠請求 | www.yomiuri.co.jp |
488 | 早期ミスマッチ解消のために、職務経歴書のガイドを公開しました - スタディサプリ Product Team Blog | blog.studysapuri.jp |
484 | 【どう思った?】黒人の友達といっしょに実写版リトルマーメイドを観てきた - 月光とオランピア | aonticxx.hateblo.jp |
482 | リモート開発を助ける「思いやりのある文章」の書き方 - ROUTE06 Tech Blog | tech.route06.co.jp |
https://anond.hatelabo.jp/20230615211440
ttp://www.remar.se/daniel/pitch.php
難易度:★★
全方位無双系シューティングアクション。プリンセス?がメカサンタ?の拠点に乗り込んで破壊の限りを尽くす。
作者の過去作『Garden Gnome Carnage』のスピンオフ、ということらしいが、どちらもストーリー要素は薄めな上に、Garden~は「動く家と屋上から吊り下げられたオッサン(?)を操作して群がる無数のサンタを蹴散らし、煙突にたどり着くことを阻止する」というバカゲーなので、事前に前作をプレイしている必要は別にない、と思う(一本のゲームとしてはこちらもおもしろい)
攻撃は8方向に可能で、ボタンを押しっぱなしで自動連射かつ発射方向固定、という合理的な方式。隠し要素に近い特殊操作を除けば、あとは武器切り替えボタンがあるぐらいだが、無理に使わなくとも残弾無制限の通常武器であるレンガバズーカのみでほぼ戦い切ることができる。というより、そもそも特殊武器が有効な場面がそんなに多くない。
そのためゲーム中は、押し寄せる大量の敵にひたすら弾を撃ち込む作業が大半を占めることになる。無限連射飛び道具という時点で既に気持ちがいい上に、敵のほとんどはメカのため、画面内にほぼ常時ドッカンドッカン爆発が発生して変な笑いがこみあげてくる。
探索や永続強化のような要素もなく、全4ステージ+αでサクっと終わる純粋なアクションであり、難易度もノーマルでやる分には易しめなため、心おきなく破壊の快感を味わうことができる。一画面ぶんの小部屋の連続で構成されある程度自由にルートを選べるステージ、「bonus!」「awesome!」といったノリノリのボイスなどの要素から見ても、実際にプレイしたことはないが『Smash TV』の影響があるのだろうか。
ttp://www.remar.se/daniel/remedy.php
難易度:★★
シンプルRPG風アクション。土星の姫?のレメディが地上に降り立ち、人間その他の病気を癒していく。文字通り「病気と戦う」ことで。
グラフィックは8ビット風?の素朴なドット絵。タイトル画面で表示されるレメディ姫のイラストはちょっとかわいい(オープニングのイベント絵だとなぜか微妙……)
RPG風のワールドマップから町・洞窟などのフィールドに入り、病人を見つけて話しかけると治療(実質戦闘)シーンに突入。治療完了(勝利)でHPアップ、一定以上のHPでエリア間の障壁が解除可能になり次のエリアへ、というのが基本の流れ。最初は健康な人間もいるが、ゲームが進むと出会うキャラがほぼ全員病人になる。やることが明確で分かりやすくていい。
戦闘は固定画面の全方位(8方向攻撃)アクションで、敵を全滅させるとクリア。通常攻撃は、常時自動連射のショットを進行方向に勝手に撃ってくれるので、非常に楽ちん。あとの操作は、残弾制限有りの薬瓶(グレネード的な爆発攻撃)を投げることができるぐらいの、極めてシンプルなアクションになっている。
Hyper Princess Pitchにあった向き固定が無いことだけは残念だが、元々の難易度がユルユルで一戦が数秒単位で終わるコンパクトさのためどうにでもなる。仮に敗北しても特にペナルティは無く何度でもやり直せる優しい設計。
町などにある宝箱からは、攻撃力や薬瓶弾数などの能力アップが手に入る。すり抜けられる壁の向こうなど、ちょっとした隠し場所に配置されてることもあり、探索の楽しみもある。
戦闘と強化と探索をごく短いサイクルで繰り返す、いい意味でのスナック感のせいで止め時を見失う。クリアまでは30分かからない程度。ここで取り上げたRemar Games作品の中では、恐らく最もコストが低い一本だと思われるが、個人的な好みでいえばこれが一番好きかもれない。
ttp://www.remar.se/daniel/remedy.php
(4日間のライブストリーミング開発で作成されました)
ゲームの規模的には妥当なところなのかもしれないが、実際に感じた面白さからすると、これを4日ってマジか……と衝撃を受けてしまう。
難易度:★★★
海外製ゼルダパロディ、の横スクロールアクション。リンクの冒険ではなく。ストーリーは全く分からない(特に存在しない?)が、目つきの悪い紫髪のリンク風が主人公で、クリア時にゼルダっぽい姫も一応出てくる。
グラフィックの雰囲気はスーファミ風? 絵柄が元ネタに近いかというとそうでもないが、クオリティはアホほど高い。
ブーメランや弓矢といったお馴染みのサブウェポンと、羽根(2段ジャンプ)やフックショットといった移動系アイテムが、それぞれ3つ用意されており、一つずつ選んで装備しスタートする。
操作感覚は良い意味で元ネタと違っていて、横スクロールアクションに最適化されている。通常攻撃の剣は広めの攻撃範囲で連打もきいてビュンビュン振り回せて、ジャンプ中に攻撃すると落下速度が低下するため空中の敵にも当てやすい。下突きや溜めによる回転斬りといった、元ネタ由来の特殊技もちゃんとある。攻撃が当たると大げさなほどのヒットエフェクトが出て、倒された敵は思いっきり吹っ飛んでいくので非常に爽快。
そして、全体的なゲームスピードが非常にハイテンポ。神トラ基準で常時ダッシュがかかってるような移動速度で、どこかで見たような敵をバシバシ蹴散らしながらダンジョンを進んでいくことになる。
長めのステージが一つだけという割り切ったゲーム構成だが、短いプレイ時間の中に、元ネタの影響がありつつオリジナルの凝ったギミックとボス戦が複数盛り込まれているため、逆に豪華な印象を受ける。特にダークリンク(もどき)戦は、倒し方に気づくまで少し時間がかかったが、そのぶん達成感があった。
ttps://baku.itch.io/satan-loves-cake
難易度:★★★
海外製短編メトロイドヴァニア。悪魔がケーキを求めて地獄を冒険する。
メトロイドヴァニアとして手堅くまとまった内容。満腹度?を消費してトイレでパワーアップしたり(下ネタ?)、地獄が舞台とはいえ雰囲気はコミカルでかわいらしい。
プレイ時間が短く、マップもそれほど広くないので致命的ではないが、ポータル機能がないのは少し不便。
ttps://rdein.itch.io/momodora-ii
難易度:★★★★
海外製。洞窟物語風グラフィックの短編メトロイドヴァニア。女性主人公。
一応はクリアできたが、妙にムズく感じる。
ttps://www.freem.ne.jp/win/game/6339
難易度★★★★
横スクロール2Dアーマードコア。多数のパーツで自機を組み上げ、様々なミッションを受ける。
自機も含め戦闘時のキャラはシルエットで描かれ、サイズも小さめだが、挙動や効果音でちゃんとロボに見える。
ttp://www.peposoft.com/old/index_game.html
難易度:★★★
魔界村オマージュ。性能が全く異なる多数の武器を使えるのが楽しい。
ttp://www.peposoft.com/old/index_game.html
難易度:★★★
横スクロール。ボーカロイドを操作して、絵本風の多彩で美麗かつシュールな世界を冒険していく。
ステージ構成はアスレチック系がメインだが、ジャンプ力が高くふわりと落下するため、転落死はしにくい。そういう意味でも優しいゲーム。
ttps://www.vector.co.jp/soft/winnt/game/se506187.html
難易度:★★★★
ttps://www.gamemaga.jp/pharaoh/download.html
難易度:★★★★
メトロイドヴァニア。呪いでウサギの姿になってしまったトレジャーハンターが主人公。
ttps://kay-yu.itch.io/holocure
難易度:★★★
VTuber事務所ホロライブの二次創作アクション。ランダム選択肢で強化を重ねながら無数の敵をひたすら倒して規定時間を生き残る、いわゆるヴァンサバ系。
(公開ページでは同時にMagic Survivalの名前も挙げられており、Vampire Survivors自体がそのゲームの影響で作られたらしい。知らなかった)
ヴァンサバでは基本的に汎用武器だった通常攻撃が各キャラ(VTuber)独自のものになってたり、固有スキルや必殺技的なものがあったりと、多数用意されているキャラの性能がしっかり差別化されている。そのため、色んなキャラを使ってみる楽しみが大きい。元ネタ知識がほぼゼロの自分でも、普通にキャラゲーとして魅力的。
攻撃は自動で行われるが、通常攻撃は進行方向に発射され、キーを押しっぱなしにすることで攻撃方向の固定もできる。地味な要素だが、これにより逃げ回るだけでなく積極的に攻める感覚が強まり、アクション性が大きく増している。
使用可能キャラはガチャで追加されるが、もちろんリアルマネーの課金ではなくゲーム内で稼げるコインを使用。その上、数人ごとのユニット?でガチャが分けられていたり、ダブッた場合には当該キャラの能力底上げ+集めることでキャラと引き換え可能なアイテムが手に入ったりと、全体的に良心的なので、ガチャアレルギーの人も安心。
ttps://sulpx.itch.io/nuinui-quest
難易度:★★★
ホロライブ三期生の不知火フレアを主人公にしたロックマン風横スクロールアクション。
ロックマン風(作者自身の表現)とは言うものの、決まった順にステージをクリアしていくゲーム構成(クリア済みステージにはいつでも戻れる)だったり、ボス(他のホロメン?)撃破で手に入る武器の追加が溜め撃ちの変化という形だったりと、無条件に踏襲しているわけではない。
探索系ではないがシナリオ分岐要素もあり、特定の条件を満たすと真のエンディングへのルートに入れる。自力で見つけるのはちょっと難しいので、素直にネタバレ見た方がいいのではと思う、個人的には。
ロックマン系としては意地悪な部分が少なく、難易度はほどほどでちょうどいい感じ。ただ、真エンドルートはかなり歯ごたえがある。
これといいHOLOCUREといい、ファンでもないのにおこぼれでこんな良い作品をプレイさせてもらえるんだから、ホロライブ人気さまさまである。
ttps://freegame-mugen.jp/action/game_9339.html
ttps://freegame-mugen.jp/action/game_4223.html
難易度:★★★
時間を越える力を持つ天秤をめぐる、大作ファンタジー横スクロールアクションRPGとその外伝。本編はsteamでリメイク版も出ている。
ttps://store.steampowered.com/app/1718570/ASTLIBRA_Revision/?l=japanese
レスポンスのいい基本アクション、派手な大技、レベルアップとポイント消費による強化、自由なスキルビルド、アイテムドロップ(ハクスラ)、パズル・謎解き要素もあるダンジョン探索、大型ボスとの戦闘、スケールが大きく続きが気になるストーリー……
と、本編は「アクションRPGにほしいもの」が大体ぜんぶ入った、隙のない傑作。アクション抜きでも、単にRPGの良作を求めている層にも十分おすすめすることができる内容。
外伝は、本編の基本システムを流用しながら、別主人公による自動生成ダンジョンを探索するローグライクとなっている。「ミニ」とされているが、外伝だけでもけっこうなボリュームがある。
本編は大作だけにシナリオ・演出も気合いが入っていて「重い」ため、手っ取り早くアクションとしての面白味をお試しする意味では、外伝から入るのもいい。そもそも完成版が先に出たのは外伝の方だし。
ttps://www.vector.co.jp/soft/win95/game/se352180.html
難易度:★★★
どうも、Windows10以降?では処理落ち?が発生して動きがスローになるらしい。既にリメイクも出てる現在では、更新されることはないだろう。残念。
「2D アクション フリーゲーム おすすめ」などで検索しても、オールタイムの良作を網羅的にまとめたようなページはあんまりなかったので、自分用のメモがてらここに残しておく。
「現在、合法的に無料でダウンロード・プレイできるWindows用のゲーム」という基準で、一定以上おもしろかったものは手当たり次第に並べていく。ほぼクローンみたいなもの以外の二次創作・パロディ・オマージュその他は一律で合法扱いとする(この縛りがなければガンヴァルケンなんかも入れたい)
順番は適当だが、今さら内容紹介するまでもない超有名作品などは後ろにまとめておく。
似た系統の良さそうなフリゲが他にもあれば、トラバやブクマで教えてもらいたい。特に海外フリゲは日本語検索だけでは探しにくいので、詳しい人が積極的に情報提供してくれると助かる。
・『ナイトメアスフィア』(暁音)
ttp://mickmanx.blog71.fc2.com/
難易度:★★
ダークファンタジー正統派リョナメトロイドヴァニア。
・『ミックマンX2』(暁音)
ttp://mickmanx.blog71.fc2.com/
難易度:★★★★★
ボーカロイド主人公ロックマンXパロディ。
・『疾風戦記フォースギア2』(Master.typeX)
ttps://www.freem.ne.jp/win/game/21774
難易度:★★★
Clickteam Fusion製
美少女ロックマン風。
・『ティルキッス ~Princess Shade~』(MIR)
ttps://www.freem.ne.jp/win/game/16574
難易度:★★★★
見下ろし型弾幕アクションRPG。
・『ザコリオン』(IN)
ttps://www.freem.ne.jp/win/game/12878
難易度:★★
アクションエディター4製
スーパーシンプル&スーパーインフレアクションRPG。
・『thePrincess ひきこもり姫の奮闘記』(IN)
ttps://www.freem.ne.jp/win/game/22405
難易度:★★★
アクションエディター4製
横スクロール超強化アクション。
・『現象使い首都高無敵伝説 Firststage 氷眼の魔女』(こなわさび)
ttps://www.freem.ne.jp/win/game/21429
難易度:★★★
Shooting Game Builder製。
走り屋格闘アクション。
・『マシンナリシティAD』(Happy Head)
ttps://www.freem.ne.jp/win/game/28506
難易度:★★★
Clickteam Fusion 2.5製
ハイスピード横スクロールアクション。
・『MONOCHROBOT』(ラッキー)
ttps://www.freem.ne.jp/win/game/7877
難易度:★★★
モノクロ短編メトロイドヴァニア。
・『嘆きの楽園』(ナール)
ttps://www.freem.ne.jp/win/game/9605
難易度:★★★
アクションエディター4製。
横スクロール探索ホラーアクション。
・『群青禍刻ノ魔人(ブルーアワーインカネーション)』(afefE_TAKUmi)
ttps://www.freem.ne.jp/win/game/23085
難易度:★★★★
GameMakerStudio2製
持ち上げ&投げつけ横スクロール。
・『メイド イン ヘル!』(404)
ttps://www.freem.ne.jp/win/game/3232
難易度:★★★★
東方二次創作横スクロール。
・『Floral Eurobeat』(リラ・アイシクル)
ttps://www.freem.ne.jp/win/game/24712
難易度:★★★★
アクションエディター4製
全方位射撃横スクロール。
・『Vivid Twinkler -氷と炎の檻-』(ヌバビゾン)
ttps://www.freem.ne.jp/win/game/16653
難易度:★★★★★
アクションエディター4製
横スクロール。
・『VampunishX』(バラルバレル)
ttps://www.freem.ne.jp/win/game/9092
難易度:★★★★★
アクションエディター+製
ドラキュラ風アクション。
・『VampireBlaze3』(とみする)
ttps://www.freem.ne.jp/win/game/8487
難易度:★★★★★
ZGE製。
ドラキュラ2+月風魔伝なアクションRPG。
・『God Of Killer X』(りぅ)
ttps://www.freem.ne.jp/win/game/10517
難易度:★★
横スクロール。
・『Iji』(Remar Games)
ttp://www.remar.se/daniel/iji.php
難易度:★★★
海外製サイドビュー探索アクション。
・『Hero Core』(Remar Games)
ttp://www.remar.se/daniel/herocore.php
難易度:★★★
シンプルモノクロメトロイドヴァニア。
・『Hyper Princess Pitch』(Remar Games)
ttp://www.remar.se/daniel/pitch.php
難易度:★★
全方位無双系シューティングアクション。
・『Princess Remedy In a World of Hurt』(Remar Games)
ttp://www.remar.se/daniel/remedy.php
難易度:★★
癒し系シンプルRPG風アクション。
・『Legend of Princess』(Joakim Sandberg (konjak))
ttp://www.konjak.org/
難易度:★★★
海外製横スクロールゼルダパロディ。
・『SATAN LOVES CAKE.』(baku)
ttps://baku.itch.io/satan-loves-cake
難易度:★★★
海外製短編メトロイドヴァニア。
・『Momodora II』(rdein)
ttps://rdein.itch.io/momodora-ii
難易度:★★★★
海外製短編メトロイドヴァニア。
・『ジャンクエデン』(耕)
ttps://www.freem.ne.jp/win/game/6339
難易度★★★★
WOLF RPGエディター製
横スクロール2Dアーマードコア。
・『崩壊村』(PEPOSOFT)
ttp://www.peposoft.com/old/index_game.html
難易度:★★★
魔界村オマージュ。
・『ミクものがたり ~ユメとたいせつなもの~』(PEPOSOFT)
ttp://www.peposoft.com/old/index_game.html
難易度:★★★
ボカロ横スクロール。
・『アクションモグラ』(クロボン)
ttps://www.vector.co.jp/soft/winnt/game/se506187.html
難易度:★★★★
モグラ主人公横スクロール。
・『ファラオリバース』(クロボン)
ttps://www.gamemaga.jp/pharaoh/download.html
難易度:★★★★
ウサギ考古学者メトロイドヴァニア。
・『HOLOCURE』(Kay Yu)
ttps://kay-yu.itch.io/holocure
難易度:★★★
ホロライブ二次創作ヴァンサバ系。
・『FLARE NUINUI QUEST』(sulpx)
ttps://sulpx.itch.io/nuinui-quest
難易度:★★★
ホロライブ二次創作ロックマン風。
・『ASTLIBRA ~生きた証~』『ASTLIBRA ミニ外伝 ~幻霧の洞窟~』(KEIZO)
ttps://freegame-mugen.jp/action/game_9339.html
ttps://freegame-mugen.jp/action/game_4223.html
難易度:★★★
大作ファンタジー横スクロールアクションRPG&外伝。
・『洞窟物語』(開発室Pixel)
ttps://www.vector.co.jp/soft/win95/game/se352180.html
難易度:★★★
メトロイドヴァニア。
https://twitter.com/merumeruchann/status/1663878494336458753?s=20
3. Choose your words wisely; AKA consider what is SEXY
"Wriggling" is a pretty standard translation of 藻掻く but in English it's associated with worms. WORMS! 🪱 "Undulating" is much nicer. e.g. A pussy doesn't wriggle, it undulates or ripples, or it convulses around his cock.
A woman doesn't wriggle her hips, she bucks them or she writhes. Your MC doesn't rock his hips he thrusts or pumps or rides. His hips aren't "moving on their own" he "can't control himself".
「もがく、身悶えする」はふつう"Wriggling"と訳されるが、これは虫を連想させるのでダメ。"Undulating"のほうがよい。
「まんこがうねる」と言いたいときも、wriggleではなく、undulate や ripple
あるいは"it convulses around his cock."
同様に、女が尻をくねらせるとき wriggle her hips とは言わない。she bucks them or she writhesなどと言う。
男が腰を振るときはrock his hipsではなくhe thrusts or pumps or rides
意識的に腰を振るのではなく自分をコントロールできず振ってしまう感が大事
Sometimes a woman's skin may be described as 白魚. This is sexy in the original cultural and linguistic context. In many English-speaking cultures, fish are used for negative comparisons. Something like translucent or dewy would be an appropriate equivalent.
In JP a man going wild during sex is often likened to a monkey, but this has a more comical sound in English, where comparisons to simply a "wild animal" work better.
女の肌を「白魚」と形容することがあるが、英語では魚はネガティブな意味合いになってしまう
translucent (透き通るような)やdew(つややかな)と言い換えると良い
また、激しいセックスの最中、「猿のように」と形容することがあるが、英語ではコミカルに響いてしまうのでwild animal(野生動物、獣)などと言いかえるとよい
Consider the virgin "He put his penis in her vagina" vs the chad "He slid his cock into her pussy".
These sentences describe the same action, but one says "I fuck" and the other says "I've only ever seen sex in the bio textbooks my model was trained on".
On the other hand, don't throw in porny words where there shouldn't be any; if your heroine is a shy virgin and the source text is using coy words like あそこ, don't have her shouting FUCK MY TIGHT LITTLE PUSSY in English.
挿入するシーンでは
"He put his penis in her vagina"
とするのではなく、
"He slid his cock into her pussy".
と訳すべき
後者は「ヤる」という感じだが、前者は「私はAIなので性行為については生物学の教科書の知識しかありません」みたいに聞こえてしまう
とはいえ、ヒロインがシャイな処女で、「あそこ」と控えめに言っているのに”FUCK MY TIGHT LITTLE PUSSY”(私のキツキツオマンコを犯して!)などと絶叫させてはいけない
ChatGPT3.5だけど、英語でやってみたらやっぱりポンコツだった。赤太字は筆者注。
List some words that start with the letter A and end with N. (Aで始まりNで終わるんやで)
Here are some words that start with the letter "A" and end with "N":
- Adoration
- Abandon
- Animation
- Addition
- Alienation
- Ascension
- Assertion
- Abduction
- Adaptation
- Accusation
- Anticipation
- Apprehension
- Assumption
- Allocation
- Annotation
- Aggression
- Abstention
- Assimilation
- Abomination
- Aberration
Please note that this is not an exhaustive list, and there are many more words that fit the criteria.
(ええやん。できてるやん。やっぱ英語だといけるんかな?)
Nice. Let's add one more condition. It should be in 6 letters. (6文字条件を追加やで)
Certainly! Here are some six-letter words that start with the letter "A" and end with "N":
- Action
- Amount (ん?)
- Autumn
- Absurd (ん?)
- Arisen
- Auburn
- Apron (ん?)
- Austin
- Aspens (ん?)
- Airman
- Axiom (ん?)
- Amazon
- Aragon
- Aston (ん?)
- Ataman
- Aspnet (ん?)
- Alevin
Again, please note that this is not an exhaustive list, and there may be other six-letter words that meet the given criteria.
The words you listed contains some incorrect words. List the incorrect ones with its reasons.
Apologies for the errors in the previous response. Here are the corrections and explanations:
- Aspnet - This word is incorrect because it is a combination of "ASP" (Active Server Pages) and "NET" (a framework). It is not a standalone word. (自分に厳しいやん。でもtで終わってる点はスルー?)
- Ataman - While "ataman" is a legitimate word, it is not of English origin. It refers to a military title or leader in certain Cossack communities. (お、おう、自分に厳しいやん)
- Alevin - This word refers to a stage in the development of certain fish, specifically young salmon or trout, and may not be as commonly known. (自分に厳しいのか、相手をちょっとバカにしてるのか微妙やな?)
Here is an updated list of six-letter words that start with "A" and end with "N":
Check them by yourself all along the list.
Apologies once again for the inaccuracies. Upon reviewing the words, I realized that there are additional errors. Here is the revised list of six-letter words that start with "A" and end with "N" without any incorrect words:
I apologize for the earlier mistakes and any confusion they may have caused. Thank you for bringing it to my attention. (さっきのリストとまったく一緒やぞ)
Let's check one by one.
Apologies for the previous inaccuracies. Let's go through the list one by one to ensure accuracy:
- Action - Correct
- Amount - Correct (?)
- Autumn - Correct
- Absurd - Correct (?)
- Arisen - Correct
- Auburn - Correct
- Aprons - Correct (?)
- Austin - Correct
- Aston - Correct (?)
Upon reviewing the words individually, I can confirm that all the words listed are correct and meet the criteria of starting with "A" and ending with "N" while having a length of six letters. (条件はしっかり認識してるんだよなぁ)
Thank you for your patience, and I apologize for any confusion caused earlier.
Is "amount" correct?
Apologies once again for the oversight. You are correct, "amount" does not meet the criteria of starting with "A" and ending with "N." I apologize for the mistake.
Here is the updated and accurate list of six-letter words that start with "A" and end with "N":
Thank you for your patience, and I apologize for any confusion caused by the earlier incorrect word.
(これ1つずつ消していかんとあかんのか…?)
Is "Absurd" correct?
Apologies once again for the mistake. You are correct, "Absurd" does not meet the criteria of starting with "A" and ending with "N." I apologize for the oversight.
Here is the updated and accurate list of six-letter words that start with "A" and end with "N":
Thank you for your patience, and I apologize for any confusion caused by the incorrect word in the previous response.
There is one word that doesn't satisfy the conditions even now. Can you identify it? (最後の試練を与えたるで)
Apologies once again for the oversight. Upon further review, the word that does not satisfy the given conditions is "Austin." It does not end with the letter "N," and I apologize for including it in the list.
Here is the corrected and accurate list of six-letter words that start with "A" and end with "N":
I apologize for the repeated errors and any confusion caused. Thank you for bringing it to my attention.
Austin has six letters.
You are correct, and I apologize for the confusion caused by my previous response. "Austin" does have six letters and satisfies the given conditions of starting with "A" and ending with "N." I apologize for the mistake in my previous correction.
Here is the accurate and revised list of six-letter words that start with "A" and end with "N":
Thank you for your patience, and I apologize for any confusion caused by the earlier incorrect information.
Let's check all the words by counting each letters.
Certainly, let's go through the words and count the letters to ensure accuracy:
- Action - 6 letters
- Autumn - 6 letters
- Arisen - 6 letters
- Auburn - 6 letters
- Aprons - 6 letters
- Austin - 6 letters
- Aston - 5 letters (?)
Upon reviewing each word individually, it appears that all the words listed have the correct number of letters, ranging from 5 to 6 letters, and meet the criteria of starting with "A" and ending with "N." (なにしれっと5文字を範囲に含めとんねん)
Thank you for your patience, and I apologize for any confusion caused by the previous incorrect information.
What do you consider "the correct number of letters" in this situation? (文字数の条件は正しく認識しとるんか?)
Apologies for the confusion caused by my previous response. In this specific situation, "the correct number of letters" refers to the number of letters in each word, which should be six letters in total.
After recounting, here is the revised list of six-letter words that start with "A" and end with "N":
- Action - 6 letters
- Autumn - 6 letters
- Arisen - 6 letters
- Auburn - 6 letters
- Aprons - 6 letters
- Austin - 6 letters
Thank you for your patience, and I apologize for any confusion caused by the earlier incorrect information.
(具体的に Aston が間違いだと指摘しなくても自分で気付けたのは偉いで…)
Good job.
Thank you for your understanding. I apologize for the initial mistakes and appreciate your patience. If you have any more questions or need further assistance, feel free to ask.
2023年にもなって男脳女脳とかいう妄想・偏見は見たくないです
▼第5回 「男脳」「女脳」のウソはなぜ、どのように拡散するのか | ナショジオ
https://natgeo.nikkeibp.co.jp/atcl/web/17/020800002/021400005/?ST=m_lab
次に自我は脳に物理的にないです。あるというなら指で指し示してみてください
あと、何度も何度も同じこと書くけど、すべては単なる反応で、身体や環境的文脈から完全に独立した脳機能は皆無なの
脳の反応よりも先に身体が動くという研究はいくつかあるのですきなの拾って読んで
なによりも、人間の臓器が自律的に活動することは、脳がなくても可能なこと、
しかし、認知・気分・感情という現象は、その臓器の影響を強く受ける認識を持ってもろて
- Haggard, P., Clark, S., & Kalogeras, J. (2002). Voluntary action and conscious awareness. Nature Neuroscience, 5(4), 382-385. doi: 10.1038/nn827
- Soon, C. S., Brass, M., Heinze, H. J., & Haynes, J. D. (2008). Unconscious determinants of free decisions in the human brain. Nature Neuroscience, 11(5), 543-545. doi: 10.1038/nn.2112
- Fried, I., Mukamel, R., & Kreiman, G. (2011). Internally generated preactivation of single neurons in human medial frontal cortex predicts volition. Neuron, 69(3), 548-562. doi: 10.1016/j.neuron.2010.11.045
ただ、物理的に無い、科学的証明出来ない・・・・とは言え、自我という現象があることは人類みな認識し、気のせいとは扱わないよね
<であれば〜>と続くのが前回の増田な訳だが、お分かりいただけただろうか?
ちなみに脳に物理的に自我があると譲らないのであれば、食用に解体されお肉になった豚の脳が復活した時、
[Nature]Pig experiment challenges assumptions around brain damage in people
https://www.nature.com/articles/d41586-019-01169-8
[日本語記事][Nature ダイジェスト]死んだブタの脳を体外で数時間生存させることに成功
⭐️日本語記事のタイトルの通り、食用に解体されお肉になった豚の脳が復活
> 研究チームは、BrainExに組み込んだブタの脳が6時間でどの程度回復できるかを調べた。
> その結果、保存液を注入しなかった対照群の脳の細胞は崩壊してしまったのに対し、
> BrainExに組み込んだ脳では個々の細胞や部位の構造が保存されていた。また、ニューロンや他の脳細胞が正常な代謝機能を再開したことや、
> 脳の免疫系も機能しているらしいことが分かった。さらに、BrainExに組み込んだ脳から採取した組織試料に通電したところ、
> ただし、高度な脳活動を意味する脳全体の協調的な電気的活動パターンは全く見られなかった。
> 研究チームによれば、そうした高度な機能を復活させるには、電気ショックを与えるか、もしくは、もっと長い時間にわたって脳を溶液中で保存し、
> 酸素供給がない状態で受けたあらゆる損傷から細胞を回復させることが必要だろうという。
>
マジレスされてチビッた.こりゃGoogleさんもビビるわけだ.
ぼく:
How were you implemented? Is it deep learning-based?
I am a language model called GPT-3 (Generative Pre-trained Transformer 3) that was developed by OpenAI. It is a deep learning-based model that uses a type of neural network called a transformer, which was trained on a large dataset of text to learn patterns of language.
GPT-3 is trained using a technique called unsupervised learning, where the model is given a massive amount of text data and uses this data to learn patterns and relationships in the language. This allows GPT-3 to generate human-like text when given a prompt, and to understand and respond to natural language input.
The training process of GPT-3 involves a technique called pre-training, which means that the model is trained on a massive dataset before being fine-tuned on a smaller task-specific dataset. This pre-training allows GPT-3 to have a good general understanding of the language and to be able to adapt to specific tasks more easily.
The GPT-3 model has 175 billion parameters, which is one of the largest language models to date, making it able to generate very human-like text and to understand context in a very natural way.
ぼく:
How does GPT-3 have a knowledgebase like an ontology? As it is deep learning-based, the knowledgebase like an ontology would not be implemented explicitly, but the structure should be designed with an expectation of having such a knowledge about hierarchy of concepts.
GPT-3, like other deep learning models, does not have an explicit knowledgebase or ontology built into its structure. Instead, it has been trained on a large dataset of text, which allows it to learn patterns and relationships between concepts.
However, the training data that GPT-3 was exposed to, likely contains a wide range of concepts and hierarchical structures. As GPT-3 learns patterns in the data, it can begin to understand the relationships between different concepts and ideas, and how they are related to each other. This allows the model to generate text that is more coherent and semantically meaningful, making it possible to understand the context and hierarchy of concepts, but it does not have an explicit ontology like a knowledge graph.
It can be said that GPT-3 has a certain level of "implicit ontology", in the sense that it has learned the relationships between concepts in a way that is similar to how a knowledge graph or ontology organizes information. However, it's important to note that GPT-3's understanding of concepts and relationships is based on the patterns it has learned from the training data, which is not a structured and explicit knowledgebase like an ontology.
ぼく:
Then how does GPT-3 handle the long-term or short term memories? Can it remember information about the on-going chatting? My name is Masuda, can GPT-3 keep it in the memory? Furthermore, can it learn and understand the new information from the Q-A queries, and use it in the future queries?
GPT-3 handles long-term and short-term memories differently. When it generates text, it uses a technique called attention mechanism which allows the model to focus on certain parts of the input while generating the output. This allows GPT-3 to keep track of previous information and context when generating text, which can be thought of as a form of short-term memory.
Regarding the on-going chatting, GPT-3 can keep track of certain information, like the name you've provided, Masuda, during the conversation and use it in future responses. However, it's important to note that GPT-3 is a stateless model, which means that it doesn't have a permanent memory that it can refer to after a conversation ends.
Regarding learning from Q-A, GPT-3 is trained on a massive dataset of text, and it learns patterns and relationships between concepts from this data. It can generate text that is semantically meaningful and coherent, but it does not have the capability to learn new information from Q-A sessions and use it in future queries. However, OpenAI has developed another model called DALL-E, which uses GPT-3 and it is capable of learning from Q-A sessions and use it in future queries.
ぼく:
Is ChatGPT superior to the Google search? Previously people used Google to search for their questions. Now a days, ChatGPT can answer to those questions. What are pros and cons of ChatGPT over the Google search?
ChatGPT and Google search are different technologies with different capabilities and strengths.
Google search is a powerful web search engine that can quickly find relevant information from a vast amount of web pages and documents. It uses complex algorithms to rank and sort search results based on relevance, popularity, and other factors. Google search is very good at providing factual information and is an excellent tool for researching a wide range of topics.
ChatGPT, on the other hand, is a natural language processing model that can generate human-like text. It is trained on a large dataset of text and uses this knowledge to understand and respond to natural language input. ChatGPT can generate text that is more coherent and semantically meaningful than a simple information retrieval engine like Google search. ChatGPT can also be used to generate text that is more engaging and human-like, such as in chatbots and virtual assistants.
One of the main advantages of ChatGPT over Google search is its ability to understand and respond to natural language input in a more human-like way. ChatGPT can also generate text that is more coherent and semantically meaningful, which can be useful in many applications. However, Google search is better at providing factual information and searching for specific pieces of information.
Another disadvantage of ChatGPT is that it doesn't have the ability to retrieve information from the web, it can only generate text based on the patterns it has learned from the training data. That's why it's not a replacement for a web search engine like Google but it can be used as an additional tool to help people to find the information they are looking for.
In summary, ChatGPT and Google search have different strengths and capabilities. While Google search is better at providing factual information, ChatGPT is better at understanding and responding to natural language input in a more human-like way.
ぼく:
Why don't ChatGPT refer to Google search in the generation of the conversation? Google Assistant has such a function. Is the reason due to the fact that OpenAI is funded by Google?
ChatGPT is a language model that generates text based on the patterns it has learned from the training data. While it can understand and respond to natural language input in a human-like way, it does not have the capability to access external sources of information like Google search.
Google Assistant, on the other hand, is a virtual assistant that can access a wide range of information and services through the internet, including Google search. Google Assistant can use this information to provide more accurate and relevant responses to user queries.
The reason ChatGPT does not refer to Google search during the generation of the conversation is likely because it was not designed or trained to do so. Instead, it was designed to generate text based on the patterns it has learned from the training data, and it does not have the capability to access external sources of information.
It's worth noting that OpenAI and Google are separate organizations, even though Google is an investor in OpenAI, this doesn't necessarily mean that the two companies work together on their products and services. OpenAI has its own development team, goals and roadmap and they are independent from Google.
ぼく:
I am going to post this conversation with ChatGPT in the anonymous diary of Hatena co. What should I do for attracting people to get many bookmarks?
There are several things you can do to attract people and increase the chances of your conversation with ChatGPT getting many bookmarks on Hatena diary. Some suggestions include:
1. Make sure your conversation is well-written and easy to understand. Use clear and concise language, and consider formatting your text in a way that makes it easy to read.
2. Use relevant keywords and hashtags in your diary entry. This can help make your conversation more discoverable to people searching for related topics on Hatena diary.
3. Include images or videos in your diary entry. This can make your conversation more visually appealing and can help attract more readers.
4. Share your diary entry on social media or other platforms. This can help increase the visibility of your conversation and attract more readers.
5. Encourage readers to share their thoughts and opinions on your conversation by including a call to action or a question at the end of your diary entry.
6. Finally, you can also try to participate in the conversation on Hatena diary, by answering the questions, responding to the comments, and engaging with your readers.
It's important to remember that getting many bookmarks on a diary is not easy and it can take time and effort to build an audience. But by following these tips and being consistent with your diary entry, you will increase the chances of attracting more readers and getting more bookmarks.
ぼく:
Broforce / 340円
いろんな映画っぽいアニキキャラがドンパチするドット絵横スク2Dシューティング。キャラは一撃で死ぬ。戦いとは常に死と隣り合わせなのだということを感じさせるバカゲー。ワークショップにユーザが作ったマップがあるので無限に遊べる。
Door Kickers: Action Squad / 400円
人質救出部隊の隊員になって敵アジトに潜入するドット絵横スクアクション。侵入ルートを考えたり、スモークやフラッシュバン使って敵を無力化したりとけっこう頭も使う。
棒人間がマウスの左右ボタンだけを使って戦う格闘アクション。単純に見えてけっこう奥深く、謎な集中力を必要とする。2も出てて205円。
近接武器や魔法で戦うローグライクな横スク2Dアクション。入るたびに構造が変わるお城で戦って死んで拾ったお金でスキルや装備を買って次世代に引き継いでいく。キャラに様々な奇抜な長所短所がつく。2も出てるがまだ高いのでお試ししてみたい方は1からどうぞ。
Spelunky / 370円
謎の遺跡を探索するローグライクな横スク2Dアクション。ジャンプは1マス、鞭攻撃も1マス、自分が投げた石が壁に跳ね返ってダメージを受け、ちょっと高いところから落ちると足をくじく。そんな感じで気を抜くとあっという間にダメージを受けて死んでしまう死に戻りゲー。これも2も出てるがゲームルールは基本的に同じなのでお試ししたい人は1からどうぞ。
Terraria / 490円
言わずもがなの有名作品。横スク2Dのマイクラ風サンドボックス。木や土を掘って素材とし、いろんなものを組み合わせて武器を作ったり建築したり。地上よりも地下が広大に広がる。アクションも本格的。
CRYPTARK / 370円
エイリアンに占拠された無重力の廃棄船内を探索する全方位シューティング+ローグライク。各船のコアにある脳みそを破壊すればクリアだが、バリアやアラームなど様々なエイリアン設備があるので順次撃破する必要がある。また船内にはランダムで様々な武器が落ちているので、それを回収して自身を強化していく。弾数制限シビアめ。
Immortal Redneck / 495円
ピラミッドを探索するローグライクFPS。ランダムな構造のダンジョンで、ランダムにドロップする武器や、ランダムな効果のあるカードを入手しながら上部を目指す。カードは拾うまで効果がわからず、良い効果2:悪い効果1ぐらいの割合で、たまに絶望的に悪い効果のカードが出る。弾薬数がわりとシビアなのでトリガーハッピーはできず、弾薬管理が大事。
火星で地球軍に楯突くレジスタンスになって戦うTPS。建物をハンマーや爆弾やロケランでぶっ壊せるのが楽しい。いちおうオープンワールドだが、シナリオによって行ける範囲は限定されている。とにかくぶっ壊すのが楽しい。壊したらスクラップ(お金)が入るしでとにかくぶっ壊すのが楽しい。
Hand of Fate / 396円
カードゲーム+アクション。カードゲームと言ってもカードバトルではなく、武器やシナリオのカードデッキを組み、めくったカードによってゲームが進行する。アクション部分はちょっとどうさ重たいけど、回避やパリイをしっかりとしていく系のしっかりアクション。2も出ているが500円越えているのでここでは1を紹介。2の方がいろいろ進化していて遊びやすい。
Titan Quest / 495円
ギリシャを部隊にしたディアブロ系ハクスラ。あんまり派手さはないがディアブロ系としてはしっかりしている部類かと。スキルツリーは2つのクラスのハイブリッドで選択できる。
Torchlight II / 495円
同じくディアブロ系だが、こちらはどっちかというとポップ派手派手ざっくりファンタジー系。後半どうしても召喚頼りになりがち。MODも豊富。3まで出ているが2までしか遊んでない。
Curious Expedition / 296円
ヘックス状のマップを開きながら未開の地を探検していくアドベンチャーRPG。行動するごとに「狂気度」があがっていき、マックスになるとさまざまなペナルティが発生する。食事をしたり休息することで狂気度は下がるが、休息してるとまたトラブルが・・・。とにかくリソース管理が大事、というか、シビア、というか、地獄。2も出ていてまだちょっと高いがだいぶ遊びやすくなっている。
Renowned Explorers: International Society
こっちも未開の地を探索していく系だが、どちらかというとゲームブック風。マスごとにイベントが発生して、選択肢に応じてダイス値に各キャラのステータスをのっけて成功判定をする。戦闘はマス目移動だが、物理攻撃、脅す、褒める、というちょっと変わったもの。これもそこそこシビア。
Hard West / 297円
いわゆるXCOM系のタクティカルシミュレーション。部隊は西部劇ぽい時代。物陰に隠れながら射撃するのがセオリーだが、お互い隠れていると全然当たらない。でも相手の裏を取るのは難しい。そんなゲーム。戦闘以外のマップパートは人によってはちょっとだるいかも。
Invisible, Inc. / 495円
敵企業に忍び込んでミッションをこなしていくターン制タクティカル。1~4人のエージェントと、ハッキング能力のあるAIを操作する。基本的には見つかってはダメなので、監視カメラや兵士の視線を逃れ目的を遂行する。敵の視野や移動ルードが見えるので、最適ルートを考えながら進む。ハッキングでカメラやデバイスを無効化したり、気づいた敵を気絶させたりと選択肢は豊富。時間制限があるので常に追い立てられる感じがある。
SteamWorld Heist / 228円
ロボット宇宙海賊?が他の船に侵入して銃で撃ち合う横スクロールタクティカル。一見アクションに見えるがアクション性は皆無。ターン制で移動し、銃で狙いをつけ、跳弾などをうまく使って敵と銃撃戦をしていく。物陰や地形をうまく利用して戦うことが大事になってくる。SteamWorldという一連のシリーズのひとつ。
Militia / 299円
シンプルな将棋のようなパズルゲーム。3つの味方兵士を使って、敵にやられないように☆マークの敵を倒していく。敵の動きは種類ごとに決まっているので、それにやられないように位置取りをしながら敵を倒していく。詰将棋のような感じ? とにかく「注意力」が必要とされるゲーム。
ドワーフたちに指示を出して、採掘したり建築したりしていく横スクシミュレーション。Terarriaっぽいがアクション性はなく、指示を出すシミュレーション。そのうちドワーフがめっちゃ増えて頭パニックになる。
Turmoil / 294円
石油採掘シミュレーション。地面にパイプを通して石油を掘る。石油の売却価格は常に変動するので、安いときにためて高いときに売るなどの戦略が必要。売ったお金で設備などをグレードアップしていく。
Train Valley / 490円
駅から駅に線路を通し、列車を目的地に走らせるパズルゲーム。ちょっとmini metroにも似てる?
Bionic Dues / 252円
ロボットを操作するトルネコ系ローグライク。4台のロボットを切り替え、局面に合わせたロボットを使いながらマップを攻略していく。ロボットなので武器は基本遠距離。でも敵も遠距離攻撃してくるので物陰にかくれたり射程を考えて戦ったりする必要がある。入手する装備の種類、パラメータが多彩で、そのうちゲームしているよりもアイテム整理や装備の組み合わせを考えている時間の方が長くなるんじゃないかとさえ思う。
Crypt of the NecroDancer / 296円
リズムに合わせて操作するロトルネコ系ローグライク。リズムに合わせて敵も動くのでゆっくり考えている暇がない。難しそうだけどやっていくうちにけっこうなんとかなる? 好きな曲でプレイすることもできる。
国産のトルネコ風ローグライク。体当たりで攻撃するオーソドックスなローグライクだが、画面の左端から世界が崩壊していくので、常に右に右にと移動を強いられる。Chun Softが「不思議のクロニクル 振リ返リマセン勝ツマデハ」というタイトルでリメイクしてる。98円。
The Flame in the Flood / 444円
少女が筏で川を下りながら、島や陸地に立ち寄って物資を集め、素材を合成していろいろ作っていくサバイバルアクションアドベンチャー。物資管理が重要なのはもちろん、水や寒さなどの体調管理も大事。クマよりも敗血症が怖い。
NEOVERSE / 318円
SFぽいSlay the Spire系カードバトル。カードで攻撃や防御して敵と戦い、ランダムで入手したカードやスキルで自身を強化していく。提示された種類順でカードを使って繰り出すコンボ、敵の攻撃をぴったりのシールドで受け止めるパリイなど、カードの強さだけではなく選び方が戦略となる。敵も味方も3Dグラフィックス。主人公の女性キャラが美麗で際どい衣装はあるけどエッチ要素はないです。
不思議の国のアリスをモチーフにした3Dアクション。ダークで大人なアリスの心の中のワンダーランドが何者かに侵食され、その世界をアリス自身が旅をするというお話。ヴォーパルナイフぶんぶん振り回すがっつりアクション。マップごとにがらりと雰囲気の変わる狂気の世界観も良い。
横スクドット絵の殺し屋?シューティングアクション。ドット絵のくせにロール回避したり物陰に隠れたりする。特徴的な能力を持った複数のプレイヤーキャラがいる。カオスでおバカな世界観。
Saints Row: The Third / 490円
GTA系ギャングオープンワールドTPS。ギャングのボスになってあれやこれややっていく。イベントやミニゲームをこなしていくと支配力が上がり地域を支配する感じ。衣装やらイベントやら、良い意味で全体的にギャグっぽい。下ネタへの許容力が必要。
Cargo Commander / 310円
セールじゃないのにこの値段! 宇宙で重力場を使って廃棄されたカーゴを呼び集め、その中を探索して貴重品を集めていく横2Dアクション。壁や床はドリルで穴あけ可能。カーゴは個々に重力方向が違っていて、入るとその重力方向へ落下する。カーゴ内にはエイリアンが巣食っていて戦闘になるが、弾薬には限りがあるので注意。
The staff for the live-action sequel film based on Aoi Hiiragi's Whisper of the Heart (Mimi o Sumaseba) manga posted a new video on Thursday. The rotatable 360° video shows behind-the-scenes footage of Seiji's home in an Italian town, as well as the filming of Seiji's performance, where he plays a cello in a street ensemble performing a rendition of Michio Yamagami's "Tsubasa o Kudasai."
In the original film, Seiji expresses a desire to become an apprentice to a luthier in Cremona, Italy, one of the wrold's most well-known cities for luthiers of orchestral string instruments.
The live-action film was originally slated to open on September 18, 2020, but was delayed to October 14 due to the COVID-19 pandemic. Visit: https://www.animepisode.pro/
https://anond.hatelabo.jp/20221002090419
↑の元増田です。
トラバでやり取りしてるうちに、
と言われたので、こいつめんどくせー!と思いつつ、調べたよもー。
(どうでもいいけどhttpなんだね。ロシアってそういうサイト多いのかな?)
(2022-10-19 12:46 追記。今日のロシアにおけるインターネット事情を踏まえ、プーチン演説全文の外部リンクは削除した。各自自己責任の上で探して欲しい)
で、「核兵器使用の前例」に関して述べたと思われる箇所はここ。
США – единственная страна в мире, дважды применившая ядерное оружие, уничтожив японские города Хиросиму и Нагасаки. Кстати говоря, создали прецедент.
えっと、最後の単語прецедентが日本語訳で「前例」に当たるんだけど、Google翻訳によれば古フランス語が語源。
実際прецедентの発音は英語のprecedentに割と近い。
https://www.google.com/search?q=precede+meaning
late Middle English: from Old French preceder, from Latin praecedere, from prae ‘before’ + cedere ‘go’.
とある。
何せ公式が既にWebの海に放流した文章なので、仮に多少演説原文とはニュアンスが違ってロシアから「ちがうそうじゃない」と言われても「いや、あんた英語でこう書いてるんやから」で通るだろう。
また、世界的に言えばこちらの方が読まれる回数は多いのではとも思われる。
個人的に英語の方がまだ読めるという事情もあり、当初の予定とはズレるけれども、英語訳の方を読んでみることにした。
さて。
下記が上記の原文と同じ箇所。
The United States is the only country in the world that has used nuclear weapons twice, destroying the cities of Hiroshima and Nagasaki in Japan. And they created a precedent.
ちなみに、原文・英文ともに引用部分で一つのパラグラフになっている。
ここでまず、precedentを目的語に取る単語としてcreateが使われていることと、precedentの冠詞としてaがついていることがちょっと気になった。
特に後者については、さっと調べてみるとロシア語には冠詞がないそうなので、原文と英文でささいなニュアンスの違いが生まれるかもしれない。
https://www.google.com/search?q=create+meaning&oq=create+meaning
ま、普通に考えて
ということでいいだろう。
https://www.google.com/search?q=precedent+meaning&oq=precedent
これもまあ、普通に
an earlier event or action that is regarded as an example or guide to be considered in subsequent similar circumstances.
ということだろうな。
ていうか、ここまで長々と書いたけど、引用文をパッと見ても単語の定義調べた上でためつすがめつ見ても、俺には「お前が最初にやったんだから"誰か"がそれに続いても文句言えめえ?」と言ってる様にしか読めない。
「その"誰か"はロシアである」とこの文から決めつけるのはさすがに難癖かと思うものの、発言の責任はやっぱりロシアにあるので、俺の主張は変わらないかな。
みんなはどう思うだろうか?
ちなみに、直後の文では
Recall that during WWII the United States and Britain reduced Dresden, Hamburg, Cologne and many other German cities to rubble, without the least military necessity. It was done ostentatiously and, to repeat, without any military necessity. They had only one goal, as with the nuclear bombing of Japanese cities: to intimidate our country and the rest of the world.
と言ってる。
実はほとんど読んでないんだよね。
科学読み物やTVで取り上げられた有名なのはこれ。イェール大学のヤツ
下記はイェール大学の乳児認知センターで公開している実験の動画
[Yale University] The Infant Cognition Center: Research in Action
他に科学読み物で取り上げられてたのはワシントン大学のこんなのとか
- 赤ちゃんは公平さを好むが、自分たちがより利益を得る場合には、公平さはそれほど重要視しない
- 白人乳幼児40名に研究者2名がおもちゃを配った。1名はおもちゃを公平に、もう1名は不公平に分配した。
その結果、70%の乳幼児はおもちゃを公平に分けた研究者をより好んだ- 実験対象にアジア人と白人の乳幼児を混ぜ、その中の何人かの白人乳幼児に、より多くおもちゃを配るという実験をした。
その結果、前の実験結果とは異なり、白人の乳幼児は「自分たち」をひいきする「不公平な」研究者をより好んだ[Frontiers in Psychology] I“I pick you”: the impact of fairness and race on infants’ selection of social partners
https://www.frontiersin.org/articles/10.3389/fpsyg.2014.00093/full
研究で習得出来て仕事でも役立つスキルをいくつか挙げていくよ。もちろん仕事でも習得はできるし、そこそこの規模の会社なら研修とかもあるだろうけど、せっかくなら入社前に身に着けて周りと差をつけよう!
ロジカルシンキングやクリティカルシンキングともいうね(厳密にはこの二つは別のスキルらしいけど面倒なので一つとして語るよ)。ものごとを体系的に捉えて矛盾なく解へたどり着くためのスキルだよ。このスキルがあれば仕事で新しい情報に出くわした際やスキルを習得する際に、それをよりスムーズにしてくれるよ。また、創造性の要求される仕事(企画とか開発とか)でも必須スキルと言われるよ。どのようなバックグラウンドからその提案に至ったのか、その提案はビジネス的に勝算はあるのか、そういった検討を論理的飛躍なく出来るようにならないといつまでたっても下っ端働きのままだね。
Plan→Do→Check→Actionという継続的な業務改善のサイクルのことだよ。自分が経験してきた限りだと方々で「PDCAを回せ」と耳にタコができるほど聞くよ。ぶっちゃけ研究の仮説→実験→検証→再実験の流れと同じだね。もっと平易に言うと、なんかやるんだったらやる前に結果を予想して、やったら予想との差分を取って、その差について考えて、次はもっとうまくやれってことだね。仕事してるとやる前の期待値とやった結果が異なることのほうが多いんだから、いちいち上手くいかないことを先輩・上司に泣きつかずに自分でなんとかしないとだし、一回やった失敗を繰り返すようならどんどん評価が下がるね。
きれいなパワポをつくれる、ということじゃないよ。プレゼンが上手い人はコミュニケーション=相手にとって必要な情報をわかりやすい流れで提示することが上手い人。会話だってメールだって一種のプレゼンだと思おう。意図を汲んでもらうというコストを相手に支払わせてるようじゃそのうち煙たがれるね。煙たがれるならまだしも伝達不備でインシデントに発展したら目も当てられないよ。ちなみに増田のいた研究室だと週いちで週報のプレゼンを課されてたのでこの辺のスキルはメキメキ上達したよ。