codex -C ~/projects/openclaw -m gpt-5.5-cyber time pic.twitter.com/6ANgzM1JKJ
— Peter Steinberger 🦞 (@steipete) 12 juin 2026
codex -C ~/projects/openclaw -m gpt-5.5-cyber time
SOFTWARE
-
Terminal command executing codex with GPT-5.5-cyber
By
–
-
Model improvements in diffs: structure, less repetition, file splitting.
By
–
you look at the diffs and see that the model improved structure, reduced repetition, broke apart large files etc.
-
Appshots in Codex: most useful Mac software for cmd+cmd prompts
By
–
appshots in codex is the most useful piece of software on my Mac most of my prompts these days are:
– cmd + cmd investigate this
– cmd + cmd open a PR to fix this
– cmd + cmd run the eval on these set of prompts and discussion
– cmd + cmd set a heartbeat to keep following up -
First infrastructure benchmark for agentic AI
By
–
The first infrastructure benchmark for agentic AI has arrived. An AI agent chains tens to hundreds of AI model calls, using tools, gathering context, and iterating until the task is complete. Existing benchmarks
-
Replit enables parallel agents to build multiple projects at once
By
–
New video is out! You no longer build one thing at a time on Replit.
— Replit ⠕ (@Replit) 12 juin 2026
Run parallel agents to ship a website, mobile app, video, and pitch deck from one project, all at once.
And you can now add multiple artifacts to projects you already have. pic.twitter.com/kgNPiFzzomNew video is out! You no longer build one thing at a time on Replit. Run parallel agents to ship a website, mobile app, video, and pitch deck from one project, all at once. And you can now add multiple artifacts to projects you already have.
-
New protocol enables AI agents to evolve and improve themselves
By
–
What if AI agents could evolve themselves to get better over time? Researchers from NTU, Stanford, Princeton, and others introduce Autogenesis Protocol (AGP). It separates what agents use (prompts, tools, memory) from how they improve—letting agents track versions, propose
-
Olivier Rimmel congratulates Mistral and calls for three AI providers in France
By
–
The French AI #Mistral is very advanced and very performant, not at the level of Opus, even less of Fable, but it's still very good and it's improving all the time. I want three providers like that in France. President @EmmanuelMacron, make sure there are
-
Fable excellent for coding but often seen as a cloner
By
–
Fable is actually really excellent for coding projects and games. However, most of what I've seen boils down to 'look, Fable has cloned [insert tool or game here]'. Even all my tests have been more or less that, basically. I think this only proves
-
Box Agent: Inter-library search and secure multi-document synthesis
By
–
—
.
@Box Agent is built on Deep Agents. Inter-library search
Multi-document synthesis
Structured reports
All within Box's existing security and permissions model
— -
Gemini 3.5 Live Translation and Major Update to NotebookLM
By
–
Here's what was launched this week: — Gemini 3.5 Live Translation our latest audio model for real-time speech-to-speech translation — @NotebookLM received a major update including agentic capabilities in chat, more reasoning