10. Medical Reasoning in the Era of LLMs This review categorizes techniques for enhancing LLM medical reasoning into training-time (e.g., fine-tuning, RL) and test-time (e.g., prompt engineering, multi-agent systems) approaches, applied across modalities and clinical tasks.
LLMS
-
Tool-Augmented RAG Agent Framework for Dynamic AI Search
By
–
7. Tool-Augmented Unified Retrieval Agent for AI Search Presents a production-ready framework that extends the RAG (Retrieval-Augmented Generation) paradigm to support real-time, dynamic, and transactional queries through agentic tool use.
-
Comprehensive Taxonomy of LLM Hallucinations: Intrinsic vs Extrinsic Errors
By
–
8. A Comprehensive Taxonomy of Hallucinations Presents a detailed taxonomy of LLM hallucinations, distinguishing intrinsic vs extrinsic errors and factuality vs faithfulness, and covering manifestations from factual mistakes to domain-specific failures.
-
Seed Diffusion: Discrete-State LLM for Code Generation
By
–
6. Seed Diffusion A discrete-state diffusion-based LLM optimized for code generation, achieving 2,146 tokens/sec on H20 GPUs while maintaining competitive benchmark performance.
-
OpenAI GPT-5 Launch: Essential Information and Updates
By
–
OpenAI Finally Launched GPT-5. Here's What You Need to Know…
-
Stanford CS336: Building Large Language Models from Scratch
By
–
Stanford CS336: Large Language Models from Scratch! This is a comprehensive course on LLMs, covers the full process of building one from scratch, including data collection, pretraining, transformer architecture, training, evaluation, and deployment.
-
GPT-5 Thinking dominates web development benchmarks with 65% win rate
By
–
GPT-5 (Thinking) tops the Web Dev @lmarena_ai
, winning ~65% of matchups and losing ~20%. This benchmark focuses on front-end development, fairly simple apps, so it is not representative of all coding. But OpenAI have made huge strides in front-end, given that their previous best -
GPT-5 offers improved user experience without existential concerns
By
–
I'm really enjoying GPT-5. A much better product experience that doesn't feel like it wants to kill me or take my job any more than previous models did.
-
OpenAI Codex: Complete Collection of References
By
–
Here's my full collection of things they've called Codex https://
simonwillison.net/2025/May/16/op
enai-codex/
… -
GPT-4o’s Affectionate Capabilities Resonate With Users
By
–
C’est un bon résumé GPT 4o était vraiment affectueux Il me manque