how to get the most out of codex cli:
CODE
-
Anthropic launches Claude Haiku 4.5 with 73% on SWE bench
By
–
BREAKING : Anthropic released Claude Haiku 4.5 with 73% score on SWE bench. Available on Claude apps and via API
-
Frustrated devs warned: not using AI leads to replacement
By
–
Frustrated devs driven by their ego didn't believe me when I said it last week. Mock those who code with AI by saying they're "cheating" if you want, spit on AI if you want to feel strong. But in the end, you'll just get pushed out the door! Devs who don't use AI? That's a
-
ChatGPT Apps: Powerful Full-Fledged Applications
By
–
ChatGPT Apps are very powerful and can include full-fledged applications: https://t.co/esv31rKMtS
— Greg Brockman (@gdb) 15 octobre 2025ChatGPT Apps are very powerful and can include full-fledged applications:
-
Video Translation Implementation Request for DeepLearningAI
By
–
Can you implement it to translate videos on @DeepLearningAI please I'm french
-
LangSmith Tracing: Exploring Run Types for LLM Debugging
By
–
Unlike traditional logs (or traces), which can be hard to interpret for LLM applications, LangSmith makes it easy to explore and debug with an intuitive, purpose-built UX.
Learn about the different types of runs you can create while tracing in LangSmith—and how they help you -
Build Voice-Activated AI Agents with Google ADK Course
By
–
Learn to build your own voice-activated AI assistant that can execute tasks like gathering recent AI news from the web, scripting out a podcast, and using tools to put all that into a multi-speaker podcast. See our new short course: "Building Live Voice Agents with Google’s ADK… pic.twitter.com/HVRXTD0ifd
— Andrew Ng (@AndrewYNg) 15 octobre 2025Learn to build your own voice-activated AI assistant that can execute tasks like gathering recent AI news from the web, scripting out a podcast, and using tools to put all that into a multi-speaker podcast. See our new short course: "Building Live Voice Agents with Google’s ADK
-
Snorkel’s FinQA Reasoning Benchmark Tests AI Financial Analysis
By
–
Snorkel’s FinQA Reasoning Benchmark is now live on @PrimeIntellect
! Test how well your models reason through real financial data — with multi-step tool use, SQL querying, and iterative logic. Explore it here -
AGI Jobs v0: Planetary Coordination Orchestrator Demo Released
By
–
[ AGI Jobs v0 : "The Operating System for AGI Work" ] Planetary Coordination Orchestrator A demo at the nexus of global coordination, decentralized governance, and thermodynamic economic planning GitHub : https://
github.com/MontrealAI/AGI
Jobsv0/tree/main/demo/infinity-symphony
… $AGIALPHA #AGIALPHA #ASIFirst -
8B MoE Model Support Coming to Ollama Next Release
By
–
This is not the same model. The 8B MoE is not currently supported in ollama, but it should be in the next release.