Was this about Codex CLI, Codex Cloud, GPT-5-Codex or all three?
LLMS
-
CREAO Builds Dynamic Couple Compatibility Quiz
By
–
I asked CREAO to build a Couple Compatibility Quiz it generated the entire app: – witty results
– dynamic scoring
– personality logic All from one prompt. Apps aren’t static anymore they talk back now. -
AI Analysis: OpenAI, Google and Mistral Predict the Future Prime Minister
By
–
Who will be the future Prime Minister according to AIs? We conducted an analysis, and the results are really interesting when comparing the different providers. > OpenAI, it’s the indecisive right-wing person. > Google, clearly right-wing. > And Mistral, the
-
Open vs Closed Models: Gap Narrowing, Focus Shifts to Applications
By
–
The gap between open and closed models are narrowing and I expect this trend to continue. As foundation models become commoditized on a global level, the most interesting directions from both research and commercial is not in their development but in finding new ways to use them!
-
Evolution Strategies at Scale Outperforms PPO for LLM Fine-Tuning
By
–
Evolution Strategies can be applied at scale to fine-tune LLMs, and outperforms PPO and GRPO in many model settings!
— hardmaru (@hardmaru) 7 octobre 2025
Fantastic paper “Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning” by @yule_gan, Risto Miikkulainen and team.https://t.co/CEyX6Z5ulG https://t.co/mPkXABJcQzEvolution Strategies can be applied at scale to fine-tune LLMs, and outperforms PPO and GRPO in many model settings! Fantastic paper “Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning” by @yule_gan
, Risto Miikkulainen and team. https://
arxiv.org/abs/2509.24372 -
China Dominates Open Source LLM Releases in 2026
By
–
China saved opensource LLMs between July 16th and today, these are the major releases: > DeepSeek V3.2 > GLM-4.6 (335B-A32B) > Qwen3-VL-30B-A3B (Instruct & Thinking) > Qwen3-VL-235B-A22B (Instruct & Thinking) > Qwen3-Next 80B-A3B (Instruct & Thinking) > GLM-4.5V (VLM,
-
Gemini Pro Tool Use Inconsistency Issues Reported
By
–
Yup, tried a couple times – but Gemini Pro is really inconsistent in tool use.
-
Grok improves faster than competing AI systems
By
–
Grok is improving faster than any other AI https://t.co/xZmjRuJT1l
— Elon Musk (@elonmusk) 7 octobre 2025Grok is improving faster than any other AI
-
ChatGPT Refuses Tasks Claude Readily Accepts: GPT-5 Comparison
By
–
In a reversal, ChatGPT now refuses to do many things that Claude is happy to address. (Examples from both GPT-5 Pro and GPT-5 Thinking)
-
Claude Code now supports 50+ AI models with Zen MCP
By
–
Claude Code can now work with 50+ AI models.
— Shubham Saboo (@Saboo_Shubham_) 7 octobre 2025
Zen MCP connects Claude Code with Gemini, OpenAI, Grok, and local models using Ollama for the best analysis on each task.
100% Opensource. pic.twitter.com/OlEmXeh7saClaude Code can now work with 50+ AI models. Zen MCP connects Claude Code with Gemini, OpenAI, Grok, and local models using Ollama for the best analysis on each task. 100% Opensource.