very cool! need some integration with https://
huggingface.co/docs/kernels/i
ndex
…?
@clementdelangue
-
Hugging Face Kernels integration for AI development
By
–
-
Open-Source Community Innovation in AI Development
By
–
open-source community will work their magic!
-
Hugging Face Becomes Platform for AI Agents and Builders
By
–
HF becoming the platform for agents (assisted by their humans) to use and build AI (rather than just leveraging APIs)! https://t.co/TyjLQI5ADC
— clem 🤗 (@ClementDelangue) 21 avril 2026HF becoming the platform for agents (assisted by their humans) to use and build AI (rather than just leveraging APIs)!
-
Monitoring AI Agents Tool Usage Through 10k Query Traces
By
–
Most of our usage is now coming from agents so to monitor how they use and mention our tools, with @DAKlingbeil
, we're now running regular 10k queries to all the most popular coding agents, share the traces on @huggingface and analyze the results (ex https://
huggingface.co/datasets/clem/
hf-coding-tools-traces
…). -
Open Source AI Security: Balancing Attacker-Defender Capability Asymmetry
By
–
Why? – Risk comes from capability asymmetry between attackers and defenders. Open source is what every frontier lab already trains on so defenders get the same AI firepower as attackers. With proprietary code, you're on your own. The biggest risk is someone training a model on x.com/ClementDelangu…
-
Access AI Agents on Hugging Face Spaces Instructions
By
–
go to a space and then tap "agents" on the top for instructions. For example for https://
huggingface.co/spaces/baidu/E
RNIE-Image-Turbo
… -
Open-source maintainers face harder security challenges than closed-source
By
–
totally got harder for open-source maintainers but I suspect that it got even harder for closed-source maintainers to stay safe (even if they don't necessary realize it yet because they've been breached silently)
-
Open Source vs Proprietary AI: Security and Capability Asymmetry
By
–
Why? – Risk comes from capability asymmetry between attackers and defenders. Open source is what every frontier lab already trains on so defenders get the same AI firepower as attackers. With proprietary code, you're on your own. The biggest risk is someone training a model on x.com/ClementDelangu…
-
Safety concerns depend on security investment levels
By
–
suspect they'll be much less safe than they used to but also depends how much they're investing in security