pull down to refresh

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 AI
related
Is Chain-of-Thought Reasoning of LLMs a Mirage?arxiv.org/abs/2508.01191
397 sats \ 9 comments \ @optimism 7 Aug AI
Here’s What’s Really Going On Inside An LLM’s Neural Network
116 sats \ 0 comments \ @0xbitcoiner 22 May 2024 BooksAndArticles
How LLMs Work, Explained Without Mathblog.miguelgrinberg.com/post/how-llms-work-explained-without-math
117 sats \ 2 comments \ @398ja 8 May 2024 BooksAndArticles
LLMs Can Get Brain Rotllm-brain-rot.github.io/
257 sats \ 0 comments \ @Scoresby 21 Oct AI
Deep Dive into LLMs like ChatGPTwww.youtube.com/watch?v=7xTGNNLPyMI
98 sats \ 1 comment \ @kepford 6 May AI
Context Rot: How Increasing Input Tokens Impacts LLM Performanceresearch.trychroma.com/context-rot
304 sats \ 2 comments \ @Scoresby 14 Jul AI
LLMs don’t do formal reasoning - and that is a HUGE problemgarymarcus.substack.com/p/llms-dont-do-formal-reasoning-and
200 sats \ 0 comments \ @Rsync25 11 Oct 2024 tech
Giving models more compute time might make them worse at reasoning - Anthropicarxiv.org/abs/2507.14417
313 sats \ 2 comments \ @Scoresby 31 Jul AI
Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in LLMsarxiv.org/abs/2406.02061
40 sats \ 0 comments \ @hn 5 Jun 2024 tech
Coping with dumb LLMs using classic MLsoftwaredoug.com/blog/2025/01/21/llm-judge-decision-tree
31 sats \ 0 comments \ @hn 24 Jan tech
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Deptharxiv.org/abs/2509.03867
306 sats \ 0 comments \ @optimism 7 Sep AI
Devs: LLMs are not about to take your jobs
679 sats \ 17 comments \ @halleck 17 May 2024 devs
Hidden Reasoning in LLMs: A Taxonomywww.lesswrong.com/posts/ZrgFfeWuckpwK5Lyi/hidden-reasoning-in-llms-a-taxonomy
178 sats \ 0 comments \ @carter 16 Oct 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
Reasoning LLMs are wandering solution explorersarxiv.org/abs/2505.20296
10 sats \ 0 comments \ @hn 10 Oct tech
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 AI
Apple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.com/ai/2024/10/llms-cant-perform-genuine-logical-reasoning-apple-researchers-suggest/
21 sats \ 1 comment \ @Rsync25 15 Oct 2024 tech
From Artificial Needles to Real Haystacks: Improving Capabilities in LLMsarxiv.org/abs/2406.19292
21 sats \ 0 comments \ @Rsync25 29 Jun 2024 alter_native
Overclocking LLM Reasoningroyeisen.github.io/OverclockingLLMReasoning-paper/
109 sats \ 0 comments \ @carter 9 Jul AI
LLMs aren’t world modelsyosefk.com/blog/llms-arent-world-models.html
121 sats \ 0 comments \ @carter 13 Aug AI
What We Know About LLMs (A Primer)willthompson.name/what-we-know-about-llms-primer
163 sats \ 1 comment \ @hn 25 Jul 2023 tech