These kinds of benchmarks are misleading without a joint metric showing much work was necessary by humans after the fact. How much time to clean up that 2h42m of code? Style and architecture need to make sense, not just passing tests. That's the bottleneck now: reviewing!
GENERATIVE AI
-
A prompt for generating insane UI with Gemini
By
–
wait.. i think I know a prompt for generating INSANE ui with gemini now.
-
Glenn Hutchins on AI Infrastructure Development and Expertise
By
–
i remember first meeting glenn hutchins when i was a grad student and he was so cogent on topics back then, just as he is now on the topic of ai infra build out. https://t.co/YT0krs1Lvd
— Nathan Benaich (@nathanbenaich) 20 novembre 2025i remember first meeting glenn hutchins when i was a grad student and he was so cogent on topics back then, just as he is now on the topic of ai infra build out.
-
AI model ratings: Claude and Gemini recommended, ChatGPT mediocre, others not recommended
By
–
Claude yes
Gemini yes Chatgpt so so (don’t recommend) Copilot no Perplexity no Grok no -
GPT-5.1-Codex-Max devient le modèle par défaut de Codex Cloud
By
–
GPT-5.1-Codex-Max is the new default model in Codex Cloud! There’s no selection there, it automatically uses the best model. In the CLI and VS Code extension, you can pick the one that best fits your task.
-
Google Releases Gemini 3 Pro with Advanced Agentic Coding Capabilities
By
–
Google released Gemini 3 Pro with SOTA agentic coding and reasoning!
— Sumanth (@Sumanth_077) 20 novembre 2025
Replit has it integrated into Design Mode, and the results look solid.
These examples are pretty cool. https://t.co/1iaFNSFZSCGoogle released Gemini 3 Pro with SOTA agentic coding and reasoning! Replit has it integrated into Design Mode, and the results look solid. These examples are pretty cool.
-
Unifying Customer Data with AI Zero Cost Hack
By
–
He publicado un episodio en @ivoox
: "Cómo unificar los datos de tus clientes con IA ("Hack" de 0€) #podcast -
OpenAI commits $1.4 trillion with no revenue strategy
By
–
Never in history was so much owed by so few: OpenAI has now committed to spend $1.4 trillion, with no revenue anywhere in sight to pay for it.
-
Codex AI Model Training Now Includes Windows Support
By
–
Codex training now includes Windows, should be much improved there.
-
Platform Emphasizes Image Generation Process Transparency Over Content Sharing
By
–
Nope, the rest of the internet is good for that. If we're going to have any kind of sharing on our own platform we want it to be distinguished by sharing the underlying image making process.