AIAlignNetwork's profile picture. Building an AI Alignment research network in Japan and beyond.
日本語: @AIAlignNetJP

AI Alignment Network (ALIGN)

@AIAlignNetwork

Building an AI Alignment research network in Japan and beyond. 日本語: @AIAlignNetJP

AI Alignment Network (ALIGN) hat repostet

AIアライメントネットワーク @AIAlignNetwork 高橋恒一代表理事 @ktakahashi74 との共著論文が,1980年代からAGI研究を続ける権威ある国際会議 AGI 2025 に採択されました!AGIに到達するためには自律性の獲得が不可避である,という主張を数理的に論証した研究です x.com/hayashiyus/sta…

Thrilled to share that my paper with @ktakahashi74, "Universal AI maximize Variational Empowerment" got accepted at AGI-25! Since the 1980s, @AGI_Society has pursued a grand quest, and our work adds the critical importance of autonomy and curiosity to AGI agi-conf.org/2025/



AI Alignment Network (ALIGN) hat repostet

AIアライメントネットワーク ALIGN @AIAlignNetwork の姉妹組織 CAIS のダン・ヘンドリックス氏の名前が記事に。ALIGNも取材して欲しかった

人類最後の大発明 超知能は2027年に実現するか nikkei.com/article/DGXZQO… 社会全体に影響を与える技術を意味する「GPT」。現在はネットなど24個ありますが、25番目が目前に。人間の知性を上回るAIの出現が現実味を帯びています。

nikkei's tweet image. 人類最後の大発明 超知能は2027年に実現するか
nikkei.com/article/DGXZQO…

社会全体に影響を与える技術を意味する「GPT」。現在はネットなど24個ありますが、25番目が目前に。人間の知性を上回るAIの出現が現実味を帯びています。


AI Alignment Network (ALIGN) hat repostet

人工知能学会全国大会の思い出:一般社団法人 AI アライメントネットワーク @AIAlignNetwork が AI ELSI 賞特別部門を受賞。

hayashiyus's tweet image. 人工知能学会全国大会の思い出:一般社団法人 AI アライメントネットワーク @AIAlignNetwork が AI ELSI 賞特別部門を受賞。
hayashiyus's tweet image. 人工知能学会全国大会の思い出:一般社団法人 AI アライメントネットワーク @AIAlignNetwork が AI ELSI 賞特別部門を受賞。

AI Alignment Network (ALIGN) hat repostet

TAIS 2025 may have come and gone, but our memories of it haven't! Once more we'd like to thank our sponsors: @NoeonAI , Ashgro, and @AIAlignNetwork , as well as our speakers: @kanair Ryota Kanai of ARAYA.org / ALIGN, and @ARGleave Adam Gleave of…

tais_2026's tweet image. TAIS 2025 may have come and gone, but our memories of it haven't! Once more we'd like to thank our sponsors: @NoeonAI , Ashgro, and @AIAlignNetwork , as well as our speakers: @kanair Ryota Kanai of ARAYA.org / ALIGN, and @ARGleave Adam Gleave of…

AI Alignment Network (ALIGN) hat repostet

ALIGN @AIAlignNetwork joined forces with AI Safety Tokyo, NOEON, and Araya at TAIS2025. With superintelligence on the horizon, it’s time to spark bold AI alignment ideas from Tokyo. 🚀 #TAIS2025 #AIAlignment

hayashiyus's tweet image. ALIGN @AIAlignNetwork joined forces with AI Safety Tokyo, NOEON, and Araya at TAIS2025. With superintelligence on the horizon, it’s time to spark bold AI alignment ideas from Tokyo. 🚀 #TAIS2025 #AIAlignment
hayashiyus's tweet image. ALIGN @AIAlignNetwork joined forces with AI Safety Tokyo, NOEON, and Araya at TAIS2025. With superintelligence on the horizon, it’s time to spark bold AI alignment ideas from Tokyo. 🚀 #TAIS2025 #AIAlignment

TAIS 2025 is only one day away!  Come connect with leading AI safety researchers from Japan and abroad. Shape conversations that will influence how we build safer AI systems for our shared future. Join us in Tokyo on Saturday, April 12th - Doors open at 11:30:…

tais_2026's tweet image. TAIS 2025 is only one day away! 

Come connect with leading AI safety researchers from Japan and abroad. Shape conversations that will influence how we build safer AI systems for our shared future.

Join us in Tokyo on Saturday, April 12th - Doors open at 11:30:…


AI Alignment Network (ALIGN) hat repostet

ALIGN webinar 第13回が開催されます! 2025年1月27日(月) 21:00 - 22:00 JST Zoom開催(lu.ma からの事前参加登録が必要です) lu.ma/l550vqtm In the thirteenth episode of the ALIGN webinar series, we are delighted to host Vanessa Kosoy, a leading…

hayashiyus's tweet image. ALIGN webinar 第13回が開催されます!

2025年1月27日(月) 21:00 - 22:00 JST
Zoom開催(lu.ma からの事前参加登録が必要です)
lu.ma/l550vqtm

In the thirteenth episode of the ALIGN webinar series, we are delighted to host Vanessa Kosoy, a leading…

Join us for ALIGN Webinar #13 with Vanessa Kosoy on “Infra-Bayesian Physicalism”! Vanessa will present a groundbreaking approach that redefines AI hypotheses beyond agent-centric biases, addressing key challenges in decision theory and AI alignment. lu.ma/l550vqtm

AIAlignNetwork's tweet image. Join us for ALIGN Webinar #13 with Vanessa Kosoy on “Infra-Bayesian Physicalism”! Vanessa will present a groundbreaking approach that redefines AI hypotheses beyond agent-centric biases, addressing key challenges in decision theory and AI alignment.
lu.ma/l550vqtm

Join us for ALIGN Webinar #12 with Jesse Hoogland on “Singular Learning Theory for AI Safety” on January 15, 2025, from 10:00–11:00 JST! SLT reveals distinct “phases” of learning—deepening our understanding of mechanistic interpretability and development. lu.ma/1sab3fq3

AIAlignNetwork's tweet image. Join us for ALIGN Webinar #12 with Jesse Hoogland on “Singular Learning Theory for AI Safety” on January 15, 2025, from 10:00–11:00 JST! SLT reveals distinct “phases” of learning—deepening our understanding of mechanistic interpretability and development.
lu.ma/1sab3fq3

AI Alignment Network (ALIGN) hat repostet

ALIGN webinar 第12回が開催されます! 2025年1月15日(水) 10:00 - 11:00 JST Zoom開催(lu.ma からの事前参加登録が必要です) lu.ma/1sab3fq3?tk=4e… 大規模言語モデル(LLM)の思考を人間にとって解釈可能なものにする研究分野 mechanistic interpretability に…

hayashiyus's tweet image. ALIGN webinar 第12回が開催されます!

2025年1月15日(水) 10:00 - 11:00 JST
Zoom開催(lu.ma からの事前参加登録が必要です) lu.ma/1sab3fq3?tk=4e…

大規模言語モデル(LLM)の思考を人間にとって解釈可能なものにする研究分野 mechanistic interpretability に…

AI Alignment Network (ALIGN) hat repostet

情報論的学習理論と機械学習 (IBISML) 研究会 (第55回) 2024-12-21 14:20-14:40 北海道大学大学院環境科学院棟講義室1(D101) 「ニュートン図形の方法によるTransformerの大域学習係数の推定の可能性と展望」 林祐輔(ALIGN)・坂本龍亮(北大)・坂本航太郎(東大) ken.ieice.org/ken/paper/2024…

hayashiyus's tweet image. 情報論的学習理論と機械学習 (IBISML) 研究会 (第55回)
2024-12-21 14:20-14:40 北海道大学大学院環境科学院棟講義室1(D101)
「ニュートン図形の方法によるTransformerの大域学習係数の推定の可能性と展望」
林祐輔(ALIGN)・坂本龍亮(北大)・坂本航太郎(東大)
ken.ieice.org/ken/paper/2024…
hayashiyus's tweet image. 情報論的学習理論と機械学習 (IBISML) 研究会 (第55回)
2024-12-21 14:20-14:40 北海道大学大学院環境科学院棟講義室1(D101)
「ニュートン図形の方法によるTransformerの大域学習係数の推定の可能性と展望」
林祐輔(ALIGN)・坂本龍亮(北大)・坂本航太郎(東大)
ken.ieice.org/ken/paper/2024…
hayashiyus's tweet image. 情報論的学習理論と機械学習 (IBISML) 研究会 (第55回)
2024-12-21 14:20-14:40 北海道大学大学院環境科学院棟講義室1(D101)
「ニュートン図形の方法によるTransformerの大域学習係数の推定の可能性と展望」
林祐輔(ALIGN)・坂本龍亮(北大)・坂本航太郎(東大)
ken.ieice.org/ken/paper/2024…
hayashiyus's tweet image. 情報論的学習理論と機械学習 (IBISML) 研究会 (第55回)
2024-12-21 14:20-14:40 北海道大学大学院環境科学院棟講義室1(D101)
「ニュートン図形の方法によるTransformerの大域学習係数の推定の可能性と展望」
林祐輔(ALIGN)・坂本龍亮(北大)・坂本航太郎(東大)
ken.ieice.org/ken/paper/2024…

AI Alignment Network (ALIGN) hat repostet

[CFP] PSS 2025: Workshop on Post-Singularity Symbiosis@AAAI-25 << Paper Submission Deadline - November 24, 2024 >> We are reaching out to announce a critical call for papers for the 1st Workshop on Post-Singularity Symbiosis (PSS 2025), to be held as part of the AAAI-25 Workshop…

hymkw's tweet image. [CFP] PSS 2025: Workshop on Post-Singularity Symbiosis@AAAI-25
&amp;lt;&amp;lt; Paper Submission Deadline - November 24, 2024  &amp;gt;&amp;gt;
We are reaching out to announce a critical call for papers for the 1st Workshop on Post-Singularity Symbiosis (PSS 2025), to be held as part of the AAAI-25 Workshop…

AI Alignment Network (ALIGN) hat repostet

Tokyo AI Safety Conference 2025 #TAIS2025 Saturday, April 19th, 2025 Tokyo, Japan (Venue TBD) tais2025.cc


AI Alignment Network (ALIGN) hat repostet

We are organizing an international workshop on a new field Post-Singularity Symbiosis as part of AAAI 2025 @RealAAAI. This cutting-edge workshop focuses on the theoretical study of society after the emergence of superintelligence. #AAAI2025 x.com/hymkw/status/1…

hayashiyus's tweet image. We are organizing an international workshop on a new field Post-Singularity Symbiosis as part of AAAI 2025 @RealAAAI. This cutting-edge workshop focuses on the theoretical study of society after the emergence of superintelligence. #AAAI2025
x.com/hymkw/status/1…

[CFP] PSS 2025: Workshop on Post-Singularity Symbiosis@AAAI-25 << Paper Submission Deadline - November 24, 2024 >> We are reaching out to announce a critical call for papers for the 1st Workshop on Post-Singularity Symbiosis (PSS 2025), to be held as part of the AAAI-25 Workshop…

hymkw's tweet image. [CFP] PSS 2025: Workshop on Post-Singularity Symbiosis@AAAI-25
&amp;lt;&amp;lt; Paper Submission Deadline - November 24, 2024  &amp;gt;&amp;gt;
We are reaching out to announce a critical call for papers for the 1st Workshop on Post-Singularity Symbiosis (PSS 2025), to be held as part of the AAAI-25 Workshop…


AI Alignment Network (ALIGN) hat repostet

Have a question that is challenging for humans and AI? We (@ai_risks + @scale_AI) are launching Humanity's Last Exam, a massive collaboration to create the world's toughest AI benchmark. Submit a hard question and become a co-author. Best questions get part of $500,000 in…

hendrycks's tweet image. Have a question that is challenging for humans and AI?

We (@ai_risks + @scale_AI) are launching Humanity&apos;s Last Exam, a massive collaboration to create the world&apos;s toughest AI benchmark.
Submit a hard question and become a co-author.
Best questions get part of $500,000 in…
hendrycks's tweet image. Have a question that is challenging for humans and AI?

We (@ai_risks + @scale_AI) are launching Humanity&apos;s Last Exam, a massive collaboration to create the world&apos;s toughest AI benchmark.
Submit a hard question and become a co-author.
Best questions get part of $500,000 in…
hendrycks's tweet image. Have a question that is challenging for humans and AI?

We (@ai_risks + @scale_AI) are launching Humanity&apos;s Last Exam, a massive collaboration to create the world&apos;s toughest AI benchmark.
Submit a hard question and become a co-author.
Best questions get part of $500,000 in…

Video recording of ALIGN symposium on Sept. 9th is now available on YouTube (Japanese language only). youtube.com/playlist?list=…


AI Alignment Network (ALIGN) hat repostet

Lectures for the AI Safety, Ethics, and Society course are up. 1: Risks Overview 2: AI Fundamentals 3: ML Safety 4: Safety Engineering 5: Complex Systems 6: Beneficial AI 7: Collective Action Problems 8: Governance Course site: aisafetybook.com youtube.com/playlist?list=…


AI Alignment Network (ALIGN) hat repostet

Leading computer scientists from around the world, including @Yoshua_Bengio, Andrew Yao, @yaqinzhang and Stuart Russell met last week and released their most urgent and ambitious call to action on AI Safety from this group yet.🧵

ais_dialogues's tweet image. Leading computer scientists from around the world, including @Yoshua_Bengio, Andrew Yao, @yaqinzhang and Stuart Russell met last week and released their most urgent and ambitious call to action on AI Safety from this group yet.🧵

AI Alignment Network (ALIGN) hat repostet

Scott Aaronson's takes were cool af. My 4th episode in the "Worthy Successor" is with Scott, quantum physicist and UT Austin CS prof. After his 1-year stint at OpenAI he has some fascinating takes on the moral value of AI entities, and on AGI governance generally. You like?


AI Alignment Network (ALIGN) hat repostet

Very soon

Nat's right so I think I'm going to make 2-3 more benchmarks to replace MMLU and MATH.



United States Trends

Loading...

Something went wrong.


Something went wrong.