GPT-5.5-Cyber is our most capable cyber model yet, designed for advanced, authorized defensive work: tracing vulnerable code, validating issues, developing patches, and preparing evidence for human review.
SOFTWARE
-
Announcing the world’s best free vibe coding platform
By
–
we have built the worlds best (and most used) free vibe coding platform, very proud of this : )
-
Organize large codebases with path-scoped rules in .claude/rules/
By
–
6/ For a big or messy codebase, do not pile it all into one file. Use path-scoped rules in a .claude/rules/ folder. They load only when Claude touches the matching part of your code, so your context stays clean instead of carrying everything at once.
-
Start with one CLAUDE.md file for build commands and conventions
By
–
3/ Start with one file. CLAUDE.md in your project root. Build commands, your folder layout, conventions, the "always do this" rules. Claude reads it at the start of every session. This one file does what those seven were trying to do.
-
Claude Code auto-loads specific files, not all recommended markdown files
By
–
1/ The viral advice says make persona.md, lessons.md, references.md, glossary.md, and more. Claude Code does not read most of them. It auto-loads a specific set of files. The rest just sit there unless you import them by hand.
-
Claude Code: 7 files or just one?
By
–
Everyone says to create 7 files when you start Claude Code. Anthropic's own docs say you only need one. Here's how to set it up:
-
Sakana Fugu: orchestrator rivaling Fable 5, not independent model
By
–
After examining the new Sakana Fugu model, which, as they present it, rivals Fable 5, I want to comment that this is in itself not a new independent model, but an orchestrator trained to orchestrate several different models (e.g., Opus 4.8, GPT
-
AI generates precise mechanical iris design in CAD
By
–
Use Case 4: Computer Aided Design of Mechanical Iris
— Sakana AI (@SakanaAILabs) 22 juin 2026
Can an AI generate precise, functional mechanical designs?
We tasked Fugu Ultra with creating a mechanical iris in CAD, similar to a camera aperture where multiple blades must move together to cleanly open and close a central… pic.twitter.com/Y27QDdcYipUse Case 4: Computer Aided Design of Mechanical Iris Can an AI generate precise, functional mechanical designs? We tasked Fugu Ultra with creating a mechanical iris in CAD, similar to a camera aperture where multiple blades must move together to cleanly open and close a central
-
Autonomous ML Research: Fugu Ultra improves GPT model via AutoResearch
By
–
Use Case 1: Autonomous ML Research
— Sakana AI (@SakanaAILabs) 22 juin 2026
Can an AI autonomously improve another AI’s training recipe?
We tasked Fugu Ultra with improving a small GPT model using AutoResearch. Over 14 hours on a single H100 GPU, Fugu ran > 100 experiments. It iteratively edited the training code, ran… pic.twitter.com/Gp96FEQ797Use Case 1: Autonomous ML Research Can an AI autonomously improve another AI’s training recipe? We tasked Fugu Ultra with improving a small GPT model using AutoResearch. Over 14 hours on a single H100 GPU, Fugu ran > 100 experiments. It iteratively edited the training code, ran
-
SkyRL async RL training with autonomous research agent
By
–
1/4: A couple notes on the implementation. The async RL training itself is powered by SkyRL, with the research agent’s goal being resolving setup issues (in this case a libnuma dependency) and analyzing runs autonomously.