Did some digging and see the confusion now. This is as designed, but I see how that seems confusing. Will change code so set calls are rejected unless you force, so users are steered to add calls.
INNOVATION
-
Creating AI Agent Spaces Harder Than Model Training
By
–
the struggle is real haha sounds harder for the agent to create a space than to train a model
-
Recurring AI incidents tracked over thousand occurrences
By
–
This has in fact (at various levels) happened more than 1000 times. Check out @DamienCharlotin
’s tracker and my substack essays about it. -
HuggingFace Jobs: Earn Tokens While Learning AI
By
–
1 hour – bunch of tokens – $1 on HF jobs – lots of fun and learning!
-
Agentic Search Enables Accurate Image Generation
By
–
It first conducted an agentic search on the internet for the information (all correct) and used it to generate the image. And thanks!
-
Interactive Generative Video Technology Transforms Website Experience
By
–
this looks like a website but it’s an interactive generative video 🫨 https://t.co/BIAxz5ryJk
— Yohei (@yoheinakajima) 22 avril 2026this looks like a website but it’s an interactive generative video
-
AI Tools, Agents, and Rapid Startup GTM Experiments
By
–
1) tips, stories, and experiences on leveraging AI as an individual (fav tools, workflows, etc.)
2) anything agent related
3) rapid fire reacting to or creating a whole bunch of startup ideas across categories and coming up with a quick GTM experiment -
E/acc community leads tech acceleration movement on X
By
–
For the record, the greatest community on X right now is the e/acc community. Great watching you all accelerate.
-
ClawHub Plugins Enable Flexible Technology Adoption Choices
By
–
You can create plugins on ClawHub, so everyone has a choice what to adopt. Please do not open more PRs for this.
-
W4A8 Inference Production-Ready Integration in vLLM
By
–
Excited to share our work on production-ready W4A8 inference, now integrated in vLLM! By combining 4-bit weights (low memory) with 8-bit activations (high compute), we hit the sweet spot for both decoding and prefill — up to 58% faster TTFT and 45% faster TPOT vs W4A16 on Hopper.