pull down to refresh

Don't Overthink It: A Survey of Efficient R1-style LRMsarxiv.org/abs/2508.02120
162 sats \ 2 comments \ @optimism 10 Aug 2025 AI
related
Construction Projects Still Run Over Schedule Despite Better Technologywww.e-architect.com/articles/construction-projects-still-run-over-schedule-despite-improved-technology
320 sats \ 1 comment \ @BlokchainB 9 Mar AI Construction_and_Engineering tech
AI Still Can't Think: Apple’s New Study Dispels the Myth
365 sats \ 2 comments \ @lunin 31 Jul 2025 AI
What Are Large Reasoning Models (LRMs)? Smarter AI Beyond LLMsyoutu.be/enLbj0igyx4
188 sats \ 0 comments \ @jakoyoh629 8 Nov 2025 AI
Hallucination Stations On Some Basic Limitations of Transformer-Based LMarxiv.org/pdf/2507.07505
213 sats \ 0 comments \ @0xbitcoiner 23 Jan AI
The ORCA Benchmark Evaluates How Well AIs Deal with Everyday Mathwww.omnicalculator.com/reports/omni-research-on-calculation-in-ai-benchmark
260 sats \ 0 comments \ @0xbitcoiner 27 Feb AI
Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in LLMsarxiv.org/abs/2406.02061
140 sats \ 0 comments \ @hn 5 Jun 2024 tech
Understanding Strengths & Limitations of Reasoning Models via Problem Complexitymachinelearning.apple.com/research/illusion-of-thinking
71 sats \ 1 comment \ @supratic 10 Jun 2025 tech
Planning Fallacy — LessWrong (2007)www.lesswrong.com/s/5g5TkQTe9rmPS5vvM/p/CPm5LTwHrvBJCa9h5
430 sats \ 0 comments \ @billytheked 16 Apr 2025 Construction_and_Engineering
Less is More: Recursive Reasoning w/ Tiny Networks - Alexia Jolicoeur-Martineaugithub.com/SamsungSAILMontreal/TinyRecursiveModels
338 sats \ 1 comment \ @Scoresby 8 Oct 2025 AI
Overclocking LLM Reasoningroyeisen.github.io/OverclockingLLMReasoning-paper/
139 sats \ 0 comments \ @carter 9 Jul 2025 AI
LLM generated context files reduce task performance and increase costs by 20%arxiv.org/pdf/2602.11988v1
434 sats \ 3 comments \ @k00b 3 Mar AI devs
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningwww.nature.com/articles/s41586-025-09422-z
151 sats \ 0 comments \ @carter 19 Sep 2025 AI
Confluence Labs achieves SOTA on ARC-AGI-2 scoring 97.9%www.confluence.sh/
650 sats \ 0 comments \ @k00b 24 Feb AI science
How to turn LLM Pinocchio into a real boy
12.7k sats \ 10 comments \ @Scoresby 7 Oct 2025 AI
‘Reverse Mathematics’ Illuminates Why Hard Problems Are Hardwww.quantamagazine.org/reverse-mathematics-illuminates-why-hard-problems-are-hard-20251201/
88 sats \ 1 comment \ @0xbitcoiner 2 Dec 2025 science
Why OpenAI’s solution to AI hallucinations would kill ChatGPT tomorrowtheconversation.com/why-openais-solution-to-ai-hallucinations-would-kill-chatgpt-tomorrow-265107
618 sats \ 25 comments \ @south_korea_ln 17 Sep 2025 AI
Context Rot: How Increasing Input Tokens Impacts LLM Performanceresearch.trychroma.com/context-rot
334 sats \ 2 comments \ @Scoresby 14 Jul 2025 AI
Current AI Models Have 3 Unfixable Problems • Sabine Hossenfelderyoutu.be/984qBh164fo
261 sats \ 2 comments \ @BlokchainB 19 Oct 2025 videos
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
Agentic Reinforced Policy Optimizationarxiv.org/abs/2507.19849
171 sats \ 0 comments \ @optimism 29 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