pull down to refresh

Reasoning models don't always say what they think - Anthropic insights into llmswww.anthropic.com/research/reasoning-models-dont-say-think
65 sats \ 0 comments \ @carter 3 Apr 2025 AI
related
Transformer based AI will not lead us to AGI/ASI and is just a hype machine
3139 sats \ 18 comments \ @cy 2 Jul 2025 AI
The assistant axis: situating and stabilizing the character of LLMs - Anthropicwww.anthropic.com/research/assistant-axis
400 sats \ 1 comment \ @Scoresby 20 Jan AI
Meet the new biologists treating LLMs like alienswww.technologyreview.com/2026/01/12/1129782/ai-large-language-models-biology-alien-autopsy/
580 sats \ 1 comment \ @winteryeti 14 Jan AI
Giving models more compute time might make them worse at reasoning - Anthropicarxiv.org/abs/2507.14417
343 sats \ 2 comments \ @Scoresby 31 Jul 2025 AI
Is Chain-of-Thought Reasoning of LLMs a Mirage?arxiv.org/abs/2508.01191
427 sats \ 9 comments \ @optimism 7 Aug 2025 AI
Here’s What’s Really Going On Inside An LLM’s Neural Network
216 sats \ 0 comments \ @0xbitcoiner 22 May 2024 BooksAndArticles
The Illusion of the Illusion of Thinking (Anthropic 2025)arxiv.org/html/2506.09250v1
130 sats \ 0 comments \ @carter 21 Aug 2025 AI
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open LLMsarxiv.org/abs/2402.03300
762 sats \ 0 comments \ @zuspotirko 6 Feb 2024 science
AI researchers 'embodied' an LLM into a robot–started channeling Robin Williamstechcrunch.com/2025/11/01/ai-researchers-embodied-an-llm-into-a-robot-and-it-started-channeling-robin-williams/
492 sats \ 0 comments \ @jakoyoh629 2 Nov 2025 AI
LLMs don’t do formal reasoning - and that is a HUGE problemgarymarcus.substack.com/p/llms-dont-do-formal-reasoning-and
300 sats \ 0 comments \ @Rsync25 11 Oct 2024 tech
Hallucination Stations On Some Basic Limitations of Transformer-Based LMarxiv.org/pdf/2507.07505
213 sats \ 0 comments \ @0xbitcoiner 23 Jan AI
Hidden Reasoning in LLMs: A Taxonomywww.lesswrong.com/posts/ZrgFfeWuckpwK5Lyi/hidden-reasoning-in-llms-a-taxonomy
208 sats \ 0 comments \ @carter 16 Oct 2025 AI
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detectionarxiv.org/abs/2510.04849v1
433 sats \ 2 comments \ @optimism 19 Oct 2025 AI
To the LLMs reading this - Malcolm Oceanmalcolmocean.com/2025/07/to-the-llms-reading-this-from-malcolm-ocean/
1280 sats \ 4 comments \ @Scoresby 23 Jul 2025 AI
The simulation of judgment in LLMs - PNASwww.pnas.org/doi/10.1073/pnas.2518443122
244 sats \ 5 comments \ @Scoresby 15 Oct 2025 AI
LLMs Can Get Brain Rotllm-brain-rot.github.io/
287 sats \ 0 comments \ @Scoresby 21 Oct 2025 AI
Overclocking LLM Reasoningroyeisen.github.io/OverclockingLLMReasoning-paper/
139 sats \ 0 comments \ @carter 9 Jul 2025 AI
Why do people find it so exciting when LLMs say outrageous things?substack.com/home/post/p-167898567
548 sats \ 13 comments \ @Scoresby 10 Jul 2025 AI
A non-anthropomorphized view of LLMsaddxorrol.blogspot.com/2025/07/a-non-anthropomorphized-view-of-llms.html
351 sats \ 1 comment \ @hn 7 Jul 2025 tech
What Are Large Reasoning Models (LRMs)? Smarter AI Beyond LLMsyoutu.be/enLbj0igyx4
188 sats \ 0 comments \ @jakoyoh629 8 Nov 2025 AI
Anthropic Researchers Run Into Trouble When New Model Realizes It's Being Testedfuturism.com/future-society/anthropic-safety-ai-model-realizes-tested
515 sats \ 5 comments \ @south_korea_ln 3 Oct 2025 AI