4. Open Thoughts This paper presents OpenThoughts3, a systematic recipe for curating supervised fine-tuning (SFT) data that advances the performance of open-source reasoning models.
LLMS
-
Information-Theoretic Framework for LLM Semantic Knowledge Organization
By
–
2. From Tokens to Thoughts This paper introduces an information-theoretic framework to examine whether LLMs organize semantic knowledge like humans, balancing compression and meaning.
-
18 Major AI Models Released in 6 Months: What’s Next?
By
–
Nous sommes le 8 juin, en 6 mois nous avons eu droit à : o3
Veo 3
Llama 4
Gemma 3
GPT-4.1
o4-mini
Gemma 3n
Grok 3
Imagen 4
DeepSeek R1
gpt-image-1
OpenAI Codex
Flux Kontext
Qwen 2.5 Omni
Midjourney v7
Gemini 2.5 Pro
Gemini 2.5 Flash
Claude 4 Qu'aurons nous d'ici janvier 2027 ? -
Complete Prompt Engineering Guide with Resources and Learning Materials
By
–
4. Prompt Engineering Guide The repo contains all the Guides, papers, lecture, notebooks and resources to learn and master prompt engineering.
-
Hands-On Large Language Models: complete code examples and notebooks
By
–
1. Hands on Large Language Models This repository contains the complete code examples from the book Hands-On Large Language Models. It includes notebook examples that cover everything from the introduction to language models to fine-tuning them.
-
GenAI Agents: Tutorials and Implementations Guide
By
–
2. GenAI Agents This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems. Check this out:
-
ChatGPT 4o updated with new ‘thinking’ capability before search
By
–
ChatGPT 4o is now thinking first before searching, as well as in some other cases. Silent updates
-
Large Reasoning Models Show Inconsistent Effort Across Problem Complexity
By
–
Despite the catchy title, that's not what the paper says. It says "[large reasoning models] reasoning effort increases with problem complexity up to a point, then declines…they reason inconsistently across puzzles" Is human reasoning effort ever inconsistent?
-
Why llms.txt Files Are Essential for Information Organization
By
–
In other news – hopefully y'all can start to understand why llms.txt files are so damn useful… E.g see that client down there – it now has everything it needs to know exactly where to find any info you require.
-
Feature Issue: Failed URL Loading for LLMs.txt Files
By
–
Love this feature, but it fails to load a *lot* of URLs I give it, including many of my lovely llms.txt files! :O