pull down to refresh

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org/abs/2502.17424
197 sats \ 6 comments \ @carter 14 Jul 2025 AI
related
[bitcoin-dev] ossification and misaligned incentive concernslists.linuxfoundation.org/pipermail/bitcoin-dev/2023-November/022119.html
91 sats \ 0 comments \ @Rsync25 3 Nov 2023 bitcoin
LLMs generate slop because they avoid surprises by design - Dan Fabulichdanfabulich.medium.com/llms-tell-bad-jokes-because-they-avoid-surprises-7f111aac4f96
343 sats \ 2 comments \ @Scoresby 19 Aug 2025 AI
Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversityarxiv.org/abs/2510.01171
166 sats \ 0 comments \ @Scoresby 17 Oct 2025 AI
LLMs’ impact on science: Booming publications, stagnating qualityarstechnica.com/science/2025/12/llms-impact-on-science-booming-publications-stagnating-quality/
247 sats \ 0 comments \ @0xbitcoiner 18 Dec 2025 science
Systemic Misalignmentwww.systemicmisalignment.com/
155 sats \ 0 comments \ @carter 30 Jun 2025 AI
LLM Alignment: Reward-Based vs Reward-Free Methodstowardsdatascience.com/llm-alignment-reward-based-vs-reward-free-methods-ef0c0f6e8d88?gi=90f7a78bfcff
17 sats \ 0 comments \ @ch0k1 6 Jul 2024 news
NVIDIA: Transforming LLM Alignment with Efficient Reinforcement Learningwww.marktechpost.com/2024/05/05/nvidia-ai-open-sources-nemo-aligner-transforming-large-language-model-alignment-with-efficient-reinforcement-learning/
20 sats \ 0 comments \ @ch0k1 7 May 2024 tech
Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in LLMsarxiv.org/abs/2509.21155
415 sats \ 6 comments \ @optimism 2 Dec 2025 AI
The illusion of alignmentwww.ashmann.co/the-illusion-of-alignment/
10 sats \ 0 comments \ @deSign_r 27 Aug 2025 Design
Fine-Tuning Increases LLM Vulnerabilities and Riskarxiv.org/abs/2404.04392
21 sats \ 0 comments \ @hn 12 Apr 2024 tech
Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiencesarxiv.org/abs/2510.06105
201 sats \ 1 comment \ @carter 9 Oct 2025 AI
Here’s What’s Really Going On Inside An LLM’s Neural Network
116 sats \ 0 comments \ @0xbitcoiner 22 May 2024 BooksAndArticles
The biggest Mystery of LLMs have just been solvedwww.youtube.com/watch?v=BbI8n9XZJo4
157 sats \ 0 comments \ @carter 18 Nov 2025 AI
Why do LLMs have emergent properties?www.johndcook.com/blog/2025/05/08/why-do-llms-have-emergent-properties/
61 sats \ 0 comments \ @k00b 9 May 2025 tech
Are LLMs random?rnikhil.com/2025/04/26/llm-coin-toss-odd-even
269 sats \ 1 comment \ @carter 30 Apr 2025 AI
AI Can Mirror Human Personalities: Why Experts Fear “AI Psychosis” Manipulationwww.techjuice.pk/ai-can-mirror-human-personalities-why-experts-fear-ai-psychosis-manipulation/
100 sats \ 0 comments \ @winteryeti 20 Dec 2025 AI
Researchers discover impressive learning capabilities in long-context LLMsventurebeat.com/ai/deepmind-researchers-discover-impressive-learning-capabilities-in-long-context-llms/
297 sats \ 0 comments \ @ch0k1 25 Apr 2024 tech
LLMs generate ‘fluent nonsense’ when reasoning outside their training zoneventurebeat.com/ai/llms-generate-fluent-nonsense-when-reasoning-outside-their-training-zone/
136 sats \ 0 comments \ @carter 21 Aug 2025 AI
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMsarxiv.org/abs/2512.09742
371 sats \ 2 comments \ @Scoresby 14 Dec 2025 AI
From Artificial Needles to Real Haystacks: Improving Capabilities in LLMsarxiv.org/abs/2406.19292
21 sats \ 0 comments \ @Rsync25 29 Jun 2024 alter_native
CONFIRMED: LLMs have indeed reached a point of diminishing returnsgarymarcus.substack.com/p/confirmed-llms-have-indeed-reached
20 sats \ 1 comment \ @Rsync25 10 Nov 2024 tech