It's a bit confusing that Claude chat has an "add to skills" mechanism now that makes new skills available when you are using the chat interface but, as far as I can tell, Claude Code for web does not – cc @claudeai did I miss something?
AI
-

Devin AI Explainer Gaining Popularity After Ryan Carson’s Endorsement
By
–
Reupping the @devinai explainer now that everyone is suddenly loving kloud koding because @ryancarson said so (btw devin usage has grown >50% MoM every month this year, it has shocked even scott)
-

MiniMax-M2.7 Weights to Be Open-Sourced Within Weeks
By
–
Here we go Confirmation from MiniMax’s Head of Engineering on what I have been saying: MiniMax-M2.7 weights will be opensourced within the next couple of weeks x.com/TheAhmadOsman/…
-
Small Expert Teams Drive AI Success in Specialized Domains
By
–
Finally an excuse to say pirate in a work setting Seeing so much success with 2-6 person teams, especially when deep subject matter expertise (ex: mortgages, oncology) is needed.
-
Software Testing and Bug Fixes in Development
By
–
We test a lot before releasing, but bugs still happen (for now). Which terminal are you using? Is there a specific action or tool call that tends to trigger scrolling to the top?
-
Iterative Experimentation and Parallel AI Chat Strategies
By
–
The main thing is just to keep thinking about what else you can do, even if you have a little idea, just try it out. Then parallelise heavily, I would often have 5-6 chats on the go.
-
Starlette 1.0 Release: Claude Skills Integration Experiment
By
–
Starlette 1.0 is out! I used this as an opportunity to experiment with Claude Skills, since Claude isn't yet familiar with the (minor) breaking changes in the 1.0 release compared to 0.x
-
The Future of Open Source: From Code to Data and Beyond
By
–
is the future value of "open source" code anymore? i believe it's shifting to data, provenance, protocols, evals, and weights. in that order.
→ View original post on X — @thom_wolf, 2026-03-22 23:49 UTC
-
Critique of AI performance in financial metric analysis
By
–
Mais cette étude permet juste de conclure que les IA ne savent pas reconstituer des résultats financiers à partir de métriques de base ? C'est quasiement trivial comme conclusion . Ça ne présage en rien d’une conclusion globale sur l’investissement en bourse. donc dire : Ne
-

Personal Record: 5 Billion Tokens Daily Usage Achievement
By
–
I thought my previous 5b tokens a day record was high