8/ The real setup. One lean CLAUDE.md. Let auto memory handle lessons. Add path rules when it grows, skills for workflows. Most people manage 7 files to do what one file and the tool already handle. Source: Anthropic Claude Code documentation, 2026.
GENERATIVE AI
-
Path-scoped rules keep Claude’s context clean for big codebases
By
–
6/ For a big codebase, do not pile everything 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 the context stays clean instead of carrying everything at once.
-
Anthropic lists seven real ways to steer Claude Code
By
–
2/ Anthropic lists the real ways to steer Claude Code. There are seven, and they are not files you invent. CLAUDE.md. Rules. Skills. Subagents. Hooks. Output styles. System prompt.
That is the actual list. -
Claude Code auto-loads specific files, not viral advice 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.
-
Beginners: one file, Claude builds the rest
By
–
Code beginners with Claude: everyone says to create 7 files first. You only need one, and Claude builds the rest itself. Here's how:
-
GitHub blocked by output policy in Claude Code
By
–
Claude Code for the web has just started saying "GitHub is blocked by the output policy", which is a big problem for me because most of my prompts there start with things like "clone simonw/sqlite-utils to /tmp to see the docs in
-
360 Cameras: Preparation for 3D Gaussian Splatting by Epic
By
–
Guess what 360 camera support is building up towards? 3d gaussian splatting of course! Only a matter of time before epic rolls it out. https://t.co/eP7fLoDTd6
— Bilawal Sidhu (@bilawalsidhu) 24 juin 2026Guess what, the support for 360 cameras prepares what? 3D Gaussian Splatting, of course! It's only a matter of time before Epic deploys it.
-
New release: A Practical Guide to RLHF from Packt
By
–
New release from @PacktDataML at https://
amzn.to/3PMn1ZL "A Practical Guide to Reinforcement Learning from Human Feedback (RLHF)" 𝗔𝗺𝗮𝘇𝗼𝗻 𝘀𝘂𝗺𝗺𝗮𝗿𝘆: RLHF is a powerful approach to AI alignment and human-centered machine learning. By combining reinforcement learning -
Kog publishes an ultra-fast 2B model on Hugging Face
By
–
Kog has open-sourced on @huggingface the 2B model they used to demonstrate a model running at over 3,000 tokens per second. Very cool work! https://huggingface.co/blog/kogai/kog-laneformer-2b-the-latency-first-model …
-
Multimodal AI connects 3D atomistic models with language
By
–
"Atomistic Language Models Understand and Generate Materials" Most materials AI still treats crystals and language separately, either turning atoms into lossy text formats or making LLMs call atomistic tools. This paper makes materials natively multimodal by connecting a 3D