pull down to refresh

Context Rot: How Increasing Input Tokens Impacts LLM Performanceresearch.trychroma.com/context-rot
334 sats \ 2 comments \ @Scoresby 14 Jul 2025 AI
related
Should you use "you" in your LLM prompts?x.com/BrianRoemmele/status/1998068828295877011
827 sats \ 10 comments \ @Scoresby 9 Dec 2025 AI
In a First, AI Models Analyze Language As Well As a Human Expertwww.quantamagazine.org/in-a-first-ai-models-analyze-language-as-well-as-a-human-expert-20251031/
274 sats \ 0 comments \ @0xbitcoiner 31 Oct 2025 AI
How to turn LLM Pinocchio into a real boy
12.7k sats \ 10 comments \ @Scoresby 7 Oct 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
Why language models hallucinate - OpenAIopenai.com/index/why-language-models-hallucinate/
438 sats \ 4 comments \ @Scoresby 6 Sep 2025 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
Agentic Reinforced Policy Optimizationarxiv.org/abs/2507.19849
171 sats \ 0 comments \ @optimism 29 Jul 2025 AI
Why Do Researchers Care About Small Language Models?www.quantamagazine.org/why-do-researchers-care-about-small-language-models-20250310/
40 sats \ 3 comments \ @0xbitcoiner 10 Mar 2025 AI
GDPval: Measuring the performance of our models on real-world tasks - OpenAIopenai.com/index/gdpval/
388 sats \ 8 comments \ @Scoresby 2 Oct 2025 AI
DeepPHY: Benchmarking Agentic VLMs on Physical Reasoningarxiv.org/abs/2508.05405
212 sats \ 0 comments \ @optimism 10 Aug 2025 AI
To Make Language Models Work Better, Researchers Sidestep Languagewww.quantamagazine.org/to-make-language-models-work-better-researchers-sidestep-language-20250414/
210 sats \ 0 comments \ @0xbitcoiner 15 Apr 2025 AI
Understanding Strengths & Limitations of Reasoning Models via Problem Complexitymachinelearning.apple.com/research/illusion-of-thinking
71 sats \ 1 comment \ @supratic 10 Jun 2025 tech
Prime Fields, Text Manglers and Progress Report on Indra
6263 sats \ 0 comments \ @l0k18 1 May 2023 bitcoin
Tongyi-DeepResearch
301 sats \ 0 comments \ @optimism 29 Oct 2025 AI
LLM Daydreaminggwern.net/ai-daydreaming
349 sats \ 2 comments \ @k00b 16 Jul 2025 AI
BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMsarxiv.org/abs/2510.04721
210 sats \ 1 comment \ @jakoyoh629 25 Oct 2025 AI
AI Still Can't Think: Apple’s New Study Dispels the Myth
365 sats \ 2 comments \ @lunin 31 Jul 2025 AI
Inside Miron Construction’s AI Journey: Tools, Challenges, and Winswww.autodesk.com/blogs/construction/inside-miron-constructions-ai/
50 sats \ 2 comments \ @BlokchainB 8 Aug 2025 Construction_and_Engineering
How Attention Sinks Keep Language Models Stablehanlab.mit.edu/blog/streamingllm
140 sats \ 0 comments \ @carter 8 Aug 2025 AI
Humanity's Last Examlastexam.ai/
327 sats \ 0 comments \ @StillStackinAfterAllTheseYears 4 Feb AI tech
Self-Adapting Language Modelsarxiv.org/abs/2506.10943
447 sats \ 0 comments \ @carter 13 Oct 2025 AI