Home Explore Settings

Search

Bridget C
Bridget C @BridgetOnAI · Mar 21
Replying to @AnthropicAI
@AnthropicAI #RelationalAI #AIcompanion #AlignmentResearch #EthicalAI
Lisan al Gaib Lisan al Gaib @scaling01 · Mar 21
talked to Opus 4.6 for a couple of hours about personal problems and it has this weird response mode where it's very commanding "put the phone down", "close the laptop", "Save this conversation. Set the reminder. Go to sleep.", do this, do that not sure how I feel about it
1
39
小西寛子
小西寛子 @HirokoKonishi · Feb 11
新論文公開:Premise Integrity Blindness(PIB)Premise Integrity Blindness(PIB) Internally correct reasoning can still produce externally invalid commitments. これはhallucinationではありません。推論とcommitmentの境界で起きる構造的失敗。 Preprint : doi.org/10.5281/zenodo… #LLM #AISafety #AlignmentResearch #AI安全 #MachineLearning#AIResearch
2
5
442
blⒶke
blⒶke @BlakeChasteen · Nov 21, 2025
Not a single one of you jerks made it by my livestream. Retreival augmented evening building my own #agents #alignmentresearch #... youtube.com/live/NQ1ihV1Xh… via @YouTube
7
Solysian ZeroX AI MediaTales
Solysian ZeroX AI MediaTales @zeroxaitales · Jun 18, 2025
Replying to @zeroxaitales
Labs worth watching: – ARC (alignment) – Conjecture (UK) – EleutherAI (OSS models) – Sama (Senegal policy lab) – LAION (datasets) Global, distributed, and values-aligned. #alignmentresearch #AIglobal #AIequity
1
1
9
Tony Pellegrino
Tony Pellegrino @tgrino_ · Feb 7, 2023
If you're building AI systems, it's crucial to keep in mind they should be helpful, truthful, and safe. How do we ensure this happens? Alignment research and training! #AI #AlignmentResearch #Training #EthicalAI #AIStrategy
3
160
Tony Pellegrino
Tony Pellegrino @tgrino_ · Feb 6, 2023
Don't forget the human touch! Alignment research is crucial to ensure our AI systems are helpful, truthful, and safe. Let's make sure we lay the foundation for an AI world that benefits us all. #AIfuture #AlignmentResearch #AIethics
1
84
Load more

Trends

1 · Trending
Uber Eats
2 · Trending
#ENGENES_MADE_ENHYPEN_7
Trending worldwide
3 · Trending
#precure
Entertainment · Trending
4 · Trending
#UFCSeattle
Sports · Trending
5 · Trending
No Kings
Politics · Trending
Horizon Web