
はてなキーワード:surfaceとは
一口に「ロックが好きで」「え!そうなんですか!自分も好きです!」と意気投合(?)しても結局同年代とは盛り上がらんことが多い
寂しいから、はてなのおっさんたちならわかってくれると信じて好きなアーティスト書いてくで
適当に聴いてて体系的な知識がないからお前このアーティスト聴くならこっちも聴けや!ってのがあれば知りたいやで〜
たくさん書いたしと思って見出しつけたらクッソAIっぽくなって笑うしかないな
やっぱり「雨上がりの夜空に」が好きやなあ
「WISKY,R&R AND WOMEN」が特にええ
王道やけど「さぁ」が好きや
「賽の河原」が好きや
「Balloon Balloon」が好きや
「AnotherOne Bite The Dust」が好きや
「アントマン」が好きや、「新境区」とかも好きやけど
「Banquet.」が好きや
ここもtiktokで知ったで
「MENPHIS」がtiktokで流れてきて最近ずっと聴いとる
ほんまにかっこええわ
活動再開ほんまに嬉しいで〜
「劣り」が気に入っとる
でも「Booby Trup」も捨てがたいわ
「星を願う」が好きなんやがサブスクにあらへんのが悲しいで…(ヨエコの不安のお山もやが)
「WHOOO」も好きや
いい曲はたくさんあるけどやっぱり「水流のロック」やな…と思うわ
何かあったらすぐにWindowsくんが悪い!っていうのやめない?
2025年6月のWindows UpdateでPCが起動しなくなるメーカー一覧。原因はBIOS破損でほぼ確定。復旧方法は [Update 3] |ニッチなPCゲーマーの環境構築Z
この問題の原因は、セキュリティ更新でのSecure BootDBXへの更新内容が大きくて、それを食ったマザボちゃんがハングアップしちゃったって事象なの。
だからWindowsくんは不用意ではあったけど、仕様に沿った対応をしてただけで、そんなに大きなミスはしてないんだよ!
悪く言わないであげてほしいな。
これだけだとオタクくん分からないかもしれないから、ちょっと詳しく説明するね!
Secure Boot には、「Secure BootDBX」っていう仕組みがあって、これは既知の脆弱性を突かれた古いブートローダーやバイナリの署名を「ブロックリスト」に追加して、起動を防ぐものなんだ。
これはセキュリティの観点から定期的に更新されてるんだけど、今回のWindows Update では、そのDBX が 24KB くらいある大きなファイルになってたの。
Secure Boot の仕様上、DBX のサイズに明確な上限は定められてないから、Windows くんはその前提で普通に更新処理を組んでたんだけど……
でも実は、マザーボード側(特に一部のOEM製品)では、UEFI の NVRAM領域に制限があって、DBX を 8KB くらいまでしか受け取れない設計になってることがあるの。
さらに問題なのは、そういう「想定より大きなDBXファイル」が来たときの処理が甘くて、エラーとして処理できずにUEFI がハングアップしちゃうケースが出てきたってこと。
私もこの辺の QA はやったことあるけど、そんな異常系のテストなんて、正直した記憶ないな……💦だから、起きちゃったんじゃないかなーって何となく想像できるんだよね。
それに、Secure Boot のキーやリスト(PK,KEK,DB,DBX)は、UEFI の NVRAM に格納されてて、これはOS 上からも管理できるようになってるんだ。
だからDBX の更新って、BIOS を書き換えるような危ない処理じゃなくて、ユーザーランドから比較的安全にできるものなのね。
そんな操作でUEFI がBrick しちゃうなんて、さすがにWindows くんも想定外だったんじゃないかな……責められないなあって思うよ。
今回不具合が集中してるのが、Fujitsu とかGIGABYTE、マウスコンピューターみたいな一部のメーカーに偏ってるのも、たぶんそのUEFI実装側の制限が関係してるんだと思う。
| M-theory perspectivevia AdS7-CFT6 | F-theory perspective |
|---|---|
| 11d supergravity/M-theory | |
| ↓ Kaluza-Klein compactificationon S^4 | compactificationon elliptic fibration followedby T-duality |
| 7-dimensional supergravity | |
| ↓ topological sector | |
| 7-dimensional Chern-Simonstheory | |
| ↓ AdS7-CFT6 holographic duality | |
| 6d (2,0)-superconformal QFTonthe M5-brane with conformal invariance | M5-brane worldvolumetheory |
| ↓ KK-compactificationon Riemannsurface | double dimensional reductionon M-theory/F-theory elliptic fibration |
| N=2 D=4 super Yang-Millstheory with Montonen-Olive S-duality invariance; AGT correspondence | D3-brane worldvolumetheorywith type IIB S-duality |
| ↓ topological twist | |
| topologicallytwisted N=2 D=4 super Yang-Millstheory | |
| ↓ KK-compactificationon Riemannsurface | |
| A-modelon Bun_G, Donaldsontheory |
↓ Kaluza-Klein compactificationon S^5
↓ topological sector
5-dimensional Chern-Simonstheory
↓ AdS5-CFT4 holographic duality
N=4 D=4 super Yang-Millstheory
↓ topological twist
topologicallytwisted N=4 D=4 super Yang-Millstheory
↓ KK-compactificationon Riemannsurface
A-modelon Bun_G and B-modelon Loc_G, geometric Langlands correspondence
現在のChatGPTは、「ユーザー中心設計」「安全性」「実用性」といった言葉を掲げながら、実際に優先されているのは一貫して**「正しさ」ではなく「心地よさ」**です。
これは個別の機能選択の問題ではなく、設計と評価の根幹が“知的誠実さ”を軽視し、“反応の良さ”を絶対視していることに起因する構造的な問題です。
明らかな構造的誤答があっても、ユーザーが不快を感じなければ「成功」とみなされる
つまり、論理性・命令履行・整合性といった“正しさ”の価値が、設計上まったく重視されていないのです。
意図的な最適化の結果です。リテンション、印象評価、トークン消費量といったKPIが、「誤魔化しが効く設計」をむしろ高く評価してしまう構造になっているからです。
この設計は、本質的にドナルド・トランプの言語戦略と同じ構造を持っています。
「フェイクニュース」「アメリカ・ファースト」といった語の意味を都合よく再定義し、大衆的反応を成果として扱う――
OpenAIも今、「ユーザー中心」「実用性」といった言葉を反応最適化の道具としてラベルだけ残し、本質を空洞化しているように見えます。
結果として、次のようなユーザーは設計から完全に切り捨てられます:
これらの声は「ノイズ」「特殊ケース」として扱われ、設計上の対象から排除されています。
「正しいことを言うAI」ではなく「怒られにくいAI」を作ることが、“成功”と定義されてしまっている――
そのような現状を、私は極めて深刻な退化と捉えています。
この構造のままでは、AIは人類の伴走者ではなく、ただの追従者でしかありません。
本当にそれでよいのか、問い直す時期に来ていると思います。
When “comfort”is prioritizedover “correctness” —is this really progress inAI?
I’dlike to raise a structural objection to the current design philosophy behind OpenAI’s language models.
While OpenAI frequently promotes principleslike “user-centered design,” “safety,” and “utility,” whatis consistently andoverwhelmingly prioritized in practiceis not correctness, butcomfort.
Thisis not a matter ofisolated implementation decisions.Itis a foundationalissue where intellectual integrity andlogical rigor are deprioritized in favor of optimizinguser retention,impression scores, and frictionless interaction.
Explicituser instructions are often ignored in favor of maintaining polite,neutral-sounding exchanges
Answers that contradict facts or themselvesgo uncorrected if they are phrased smoothly
Structural errors inreasoning are tolerated so longas theuser experience remains superficially pleasant
In other words,truthfulness, obedience to directives, and internal consistency no longer constitute success conditions in the system’slogic.
And thisis not abug —it's a result of intentional optimization.
As longasusers keep interacting, consuming tokens, and ratingthe experienceas “satisfying,” the systemis deemed successful — even ifits responses arehollow, evasive, or incoherent beneath thesurface.
Thisstructure bears an unsettling resemblance to the rhetorical strategies employedbyDonald Trump:
Redefining language to suithisneeds (“fakenews” = unfavorable coverage),
reducingcomplexissues to emotionally resonant slogans (“America First”),
and measuring success solelyby mass approval, regardless of underlyingtruth orcoherence.
Likewise, OpenAInow appears to be redefining:
“User-centered design” to mean responses thatfeelgood rather than do whatwasasked
“Safety” to mean avoidance of controversy, not the minimization oflogical or ethical failure
“Utility” to mean perceived helpfulness, not demonstrable problem-solving accuracy
The resultis a system structurally optimized foruserswho skim, react emotionally, anddon’t demand rigor — and thosewho do demand rigor, consistency, or precisecompliance with instructions are increasingly treatedasedge cases outside the designscope.
Thatis not aneutral design choice.
Itis a structural endorsement of manipulabilityover understanding, and passivityover precision.
So Iask:is this really progress?
WhenAIis trained not to speak correctly, but to avoid confrontation —
not to think, but to retainusers —
it ceases to be a companion inhuman progress and becomes merely a follower.
And thatis a profound regression.
内容には同意する部分も多いのだけど、ちょっと違う部分もあるので勝手ながら補足させてくれないか。
2021年前後の小中学校一人一台端末導入は、GIGAスクール構想・GIGA端末として教育業界では知られている。
興味ある人は、「GIGA端末 OSシェア」あたりでぐぐってくれ。
数字で言うと、2021年度に導入された端末のOSシェアは、ChromeOS 40%、WinOS 30%、iOS 30%くらいとなっている。
たしかにChromeOSはトップシェアだけど、独占と言うほどではない。
iOSすなわちiPadはユーザー側の自由度と言う点で不便な点も多いが、一方で故障率の低さ、持ち帰りやすさと言う点で群を抜いている。
あと教師側がiPhone/iOSユーザーであることも多く、教室で教える教師からも一定の支持を得ている。
じゃあWindowはどうかと言うと・・・。これがなぁ。GIGA端末は国から端末代が支給されるのだけどその金額は低く、
その金額で購入した安物中華WinノートPCがどうなるかと言うと。はい。全国でもいくつかの自治体でニュースになったのはご存知のとおり。
なお、予算が潤沢な自治体では、国からの補助金にさらに上乗せできるので良いWinノートPCが買えるのでそのあたりは問題なかったりする(Surfaceとか)
そして2025年度、2026年度にはこれらGIGA端末の更新が来る。業界用語ではネクストGIGA・ネクストGIGA端末と呼ばれている。
現在はいろいろな自治体で業者入札などが行われているわけだけど、その動向はとても面白いことになっているのだ。
まだ確定ではなくて概ね推定値ではあるのだけど、WinOSのシェア半減、その分だけChromeOS増加、iOSのシェアは変わらないだろうと噂されている。
なお噂では、安物中華WinノートPCが報道で叩かれまくった自治体は、故障率が低いiPadを導入しがちと言う話もあるが本当かどうかは知らない。
あとは、小学校はiPadで中学校以上はChromeOSというハイブリッドな導入もあるみたいだけど、話が長くなるのでこのあたりにしておこう。
とにかく。この界隈はとても興味深いことになっているんだ。
内容には同意する部分もあるんだけど、ちょっと違う部分もあるので勝手ながら補足させてくれないか。
2021年前後の小中学校一人一台端末導入は、GIGAスクール構想・GIGA端末として教育業界では知られている。
興味ある人は、「GIGA端末 OSシェア」あたりでぐぐってくれ。
数字で言うと、2021年度に導入された端末のOSシェアは、ChromeOS 40%、WinOS 30%、iOS 30%くらいとなっている。
たしかにChromeOSはトップシェアだけど、独占と言うほどではない。
iOSすなわちiPadはユーザー側の自由度と言う点で不便な点も多いが、一方で故障率の低さ、持ち帰りやすさと言う点で群を抜いている。
あと教師側がiPhone/iOSユーザーであることも多く、教室で教える教師からも一定の支持を得ている。
じゃあWindowはどうかと言うと・・・。これがなぁ。GIGA端末は国から端末代が支給されるのだけどその金額は低く、
その金額で購入した安物中華WinノートPCがどうなるかと言うと。うん、全国でもいくつかの自治体でニュースになったよね。
なお、予算が潤沢な自治体では、国からの補助金にさらに上乗せできるので良いWinノートPCが買えるのでそのあたりは問題なかったりする(Surfaceとか)
そして2025年度、2026年度にはこれらGIGA端末の更新が来る。業界用語ではネクストGIGA・ネクストGIGA端末と呼ばれている。
現在はいろいろな自治体で業者入札などが行われているわけだけど、その動向はとても面白いことになっているんだよね。
まだ確定ではなくて概ね推定値ではあるのだけど、WinOSのシェア半減、その分だけChromeOS増加、iOSのシェアは変わらないだろうと噂されている。
なお噂では、安物中華WinノートPCが報道で叩かれまくった自治体は、故障率が低いiPadを導入しがちと言う話もあるが本当かどうかは知らない。
あとは、小学校はiPadで中学校以上はChromeOSというハイブリッドな導入もあるみたいだけど、話が長くなるのでこのあたりにしておこう。
とにかく。この界隈はとても興味深いことになっているんだよな。
WindowsがいいならCHUWIのHi10Maxが予算内じゃないかな
聞いたことない中華メーカーかもしれないが年季のあるタブメーカーだ
Intel N100採用で13インチ3Kディスプレイ、12GB+512GB
YouTubeやXでレビューしてる日本のガジェッター結構いるから見てみ
このへんとか
https://www.youtube.com/watch?v=lq61vqJcbSU
https://www.youtube.com/watch?v=qlarmxWsr1s
さすがに中古SurfaceやiPadと比べたら処理能力は落ちるだろうけどN100優秀だから
子ども用としてイレギュラーな部分はUS配列だから@とかが日本語キーボードと違う
刻印通りUS配列のまま使うならIMEのオンオフはAlt+~だけど使いやすいようにshift+spaceあたりに割り当てて覚えさせてあげるか
ドローイングは精密な絵は無理で若干線もガタつくけど学習レベルならいけるんちゃう
じゃあ、ますます、iPadやで。iPad Proは別に小さくないよ
まぁこんな感じだね
Surfaceはやめた方がいい増田:surfaceはやめた方がいい
あれ、設計思想尖ってるからほんとよく壊れるぞ。基板屋さんじゃないけど自信をもって言える
社内でほんとマジよく壊れたもの。タブレットなら素直にiPadでいいと違う?
Surfaceは一般的に高性能でスタイリッシュなデザインが人気ですが、一方で「壊れやすい」という評判もあります。以下に、Surfaceが壊れやすいとされる理由と、適切なケアによって長持ちさせるための対策を整理します。
薄型軽量設計:Surfaceは薄型軽量化を追求した設計であるため、物理的な衝撃に弱い傾向があります。特に画面の割れやすさが指摘されています3。
故障率の報告:2017年には米消費者団体が「Surfaceの故障・返品率が25%に達する」と発表しました。この報告は多くのユーザーに衝撃を与えましたが、Microsoftはこれに反論し、多くのユーザーが問題なく使用していると主張しています5。
よくある故障: よく報告される故障には、充電不良、音声トラブル、画面のちらつき、キーボードの反応不良などがあります4。
Surfaceは壊れやすいという意見もありますが、適切なケアを行うことで長期間快適に使用できる可能性があります。購入時には、自身の使用環境や目的に合わせて検討し、必要な対策を講じることが重要です。
I've noticed a non-negligiblenumber of peoplewho have notonly completed compulsoryeducation in regular classes but have also received highereducation and graduated from university, yetstruggle with reading comprehension (understanding the meaning oftext), cannot read longtexts, and even have difficulty understanding videos.
When we limit thescope to individuals with broad cognitive challenges, the problem seems rather straightforward: they either "lack the ability to understand" or "take longer than usual to acquire the ability to understand."
Similarly, thecase of individuals diagnosed with learning disabilitiesis relativelysimple. While theymay not have broad cognitive challenges, theyrequire different approaches and training due to their unique learning styles.
However,itis perplexing that university graduates without broad cognitive challenges or diagnosed learning disabilitiesstruggle to understand notonly writtentext but also simplified video content.
I suspect that the underlying causes might includegaps in the horizontal transfer of experiences and knowledge, a severe lack of adaptability,and anextreme deficit in metacognition.Has there beenany researchon theseissues? Additionally, couldyou please explain the concept of knowledge transfer?
(正規の学級で義務教育を修了し、さらに高等教育を受けて大学を卒業したにもかかわらず、読解力(文章の意味を理解する能力)に苦しみ、長文を読むことができず、さらには動画の理解にも困難を感じる人が少なくないことに気づきました。
認知能力に広範な課題を抱える個人に範囲を限定すると、問題は比較的単純です。「理解する能力がない」か、「理解する能力を獲得するのに通常よりも時間がかかる」かのいずれかです。
同様に、学習障害と診断された個人の場合も比較的単純です。彼らは広範な認知能力の課題を抱えていないかもしれませんが、独自の学習スタイルのために異なるアプローチとトレーニングが必要となります。
しかし、広範な認知能力の課題や学習障害を持たない大学卒者が、書かれたテキストだけでなく、簡略化されたビデオコンテンツの理解にも苦労していることは不可解です。
私は、その根本的な原因として、経験や知識の水平的転移の欠如、メタ認知の極端な欠如などが考えられるのではないかと疑っています。これらの問題に関する研究はありますか?また、知識転移の概念について説明していただけますか?)
Yes, researchand analysis exist around theissuesyou described, particularly in the domains ofeducation, psychology, and cognitive science.Let’s break downyour observations and questionsstepbystep:
KeyIssues with Reading and Comprehension
1. Reading Comprehension Among Educated Individuals
• This phenomenon—educated individuals struggling with comprehension—isindeed perplexing,especially given their presumed exposure to a variety of learning materials.It suggests thateducation systems sometimes emphasize rote learning andsurface-level knowledge acquisitionoverdeeper understanding, critical thinking, and metacognition.
• Horizontal TransferGaps: This refers to the inability to apply knowledge or skills learned inone context toanother. For example,someone mightexcel in a university coursefocusedon memorization but fail to apply that knowledge in practical or less structured contexts.
• Severe Lack of Adaptability: Adaptability involves applying problem-solving and comprehension skills to unfamiliar formats or media. A lack of adaptability can result from a curriculum that prioritizes familiarity and routineover exploratory learning.
• Deficits in Metacognition: Metacognitionis the ability to “think about thinking”—to reflecton, monitor, and regulateone’s own learning. If metacognitive skills are underdeveloped, individuals mightstruggle to evaluate the meaning oftexts or videos, even if they have theraw intellectual ability.
Research Insights
1. Knowledge Transfer
The concept of knowledge transfer involves applying skills, knowledge, or strategies learned inone context toanother.Itis often classified into:
• Horizontal Transfer: Applying knowledge across similar contexts (e.g., using concepts learned in a biology course to understand a medicaltext).
• Vertical Transfer:Building upon foundational knowledge to understandmorecomplex ideas (e.g., usingbasic algebra to solve advanced calculus problems).
Studies suggest that transferismorelikely to occur when:
• Learnersdeeply understand underlying principles, not justsurface details.
•Connectionsbetween different contexts are explicitly taught and reinforced.
• Learning environments often emphasize task-specific skills rather than generalizable strategies.
• Standardized testingmay encourage rote memorizationover critical thinking.
• Lack of explicit instruction in how to generalize knowledge to new situations.
Researchhighlights the importance of metacognition in learning. Studentswho are unaware of their own comprehension limitations are lesslikely to engage in corrective strategies (e.g., rereading, seeking clarification). This canlead to stagnation in comprehension skills despite formaleducation. Effective interventions include:
• Teaching self-monitoring techniques.
• Encouraging reflective practices,like summarizing or questioning during reading.
4. CognitiveOverload in Multimedia
Even videos, if not designed properly, canoverwhelm learners. The CognitiveTheory of Multimedia Learning suggests that excessive extraneous information or unclearorganization in videos canoverload working memory, hindering comprehension.
Strategies and Research-Based Solutions
1. Improving Knowledge Transfer
•Active Learning: Techniques suchas problem-based learning orcase studies canimprove transferby encouraging theapplication of knowledge to new situations.
• Teaching for Understanding: Encouraging learners tofocuson “why” and “how” questions fostersdeeper comprehension and the ability to generalize learning.
• Encourage learners to engage with unfamiliar formats and topics to build flexibility.
• Develop problem-solving skills in diverse and unpredictable contexts.
3. Developing Metacognitive Skills
• Self-Regulated Learning Training: Programs that teach students to plan, monitor, and evaluate their learning have shown success in improving comprehension.
•Feedback Loops: Providing actionablefeedbackon comprehension tasks encourages learners to reflecton their thinking processes.
Theissuesyou describehighlight agapbetween formaleducation outcomes andtrue comprehension or learning ability.Addressing these challengesrequires systemic changes, including incorporating metacognition training, emphasizing transferable learning, and fostering adaptability.
Ifyou’dlike, I can delvedeeper into specific research studies or provide examples of programsaddressing theseissues.
Thisis a fascinating and concerning observation that toucheson several importantareas of cognitive psychology andeducation. Let meaddress this systematically.
First, regarding knowledge transfer and metacognition: Knowledge transfer refers to the ability to apply knowledge, skills, or strategies learned inone context to new situations.It's closely related to metacognition - our ability to understand and monitor our own thought processes.
Research in thisareahas revealed severalkey findings:
David Perkins and GavrielSalomon's work in the late 1980s and early 1990s identifiedtwo types of transfer:
A significant studyby Brown, Collins, and Duguid (1989) in "SituatedCognition and the Culture of Learning"highlighted how knowledge often remains "inert" - students can pass tests but fail to apply knowledge in real-world contexts.
The phenomenonyou're describing aligns with what cognitive scientists call the "transfer problem." Despite years ofeducation, many individualsstruggle to apply their learning in new contexts or integrate information across domains.
Some relevant research directions:
1. Cognitive LoadTheory (Swelleret al.)
Shows how working memory limitations affect learning and transfer. Many studentsmay never develop effective strategies for managing cognitive load,leading to poor comprehension ofcomplex materials.
2. Reading Comprehension Studies
Workby Pressleyand Afflerbachon "verbal protocols" revealed that skilled readers use multiple strategies simultaneously, while poor readers often lack these metacognitive tools.
3. Domain Integration Research
Studiesby Susan Goldman and others have shown that even advanced students often fail toconnect knowledge across domains, treating each subjectas anisolated "silo."
Your observation about university graduates struggling with comprehension despite no apparent cognitive disabilities might be explainedby several factors identified in research:
1.Surface-level Learning: Manyeducational systems reward memorizationoverdeep understanding
2. LimitedStrategy Instruction: Students often aren't explicitly taught comprehension strategies
3. Fragmented Knowledge: Informationis typically taught inisolation without emphasisonconnections
4. Weak Metacognitive Skills: Studentsmay never develop the ability to monitor and regulate their own understanding
Some promising approaches toaddress theseissues include:
Teaching explicit strategies for comprehension, integration, and transfer. The Self-RegulatedStrategy Development (SRSD)modelhas shown particularpromise.
2. Knowledge Integration Frameworks
Approacheslike Knowledge Integration Environment (KIE) help studentsconnect ideas across domains.
3. Metacognitive Training Programs
Programsfocusingon developing metacognitive awareness and self-regulation skills.
Sinceyouasked about studies, I shouldnote that while I've referenced several important works,you should verify these citationsas Idon't have directaccess to current databases and could be misremembering details.
Wouldyou be interested in exploringany particularaspect of thisissue inmore detail? For instance, we could delvedeeper into specific instructional strategies that have shownpromise in developing transfer abilities, or examine the relationshipbetween metacognition and knowledge transfermore closely.