Would you trust the current administration not to find a reason to claw back a grant?
AI
-
AutoGaze: Efficient Video Understanding with Selective Attention
By
–
Humans can see in high-res, high-FPS in real-time. Why can't VLMs?
— Baifeng (@baifeng_shi) 24 mars 2026
Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos.
📄 https://t.co/a14yqNRPlh
🌐 https://t.co/ifLNMUIL3J
🤗… pic.twitter.com/O0A0WLrkxbHumans can see in high-res, high-FPS in real-time. Why can't VLMs? Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos. 📄 arxiv.org/abs/2603.12254 🌐 autogaze.github.io 🤗 huggingface.co/collections/b… (1/n)🧵
→ View original post on X — @berkeley_ai, 2026-03-24 18:46 UTC
-
Remove Experimental Flags to Fix AI Prompts
By
–
Try removing things like –exp from your prompt, this may be causing issues. Thanks!
-
Code organization and AI agent development methodologies evolution
By
–
Oui d'ailleurs la manière dont @bcherny avait détaillé son process de code avec sa stack était déja une organisation à la clawd avant que la vague n'arrive. Et c'était aussi le principe de babyagi il y a un peu plus longtemps.
-
Code Validation Tools Essential for AI Coding Agents
By
–
As always though the trick is to arm them with a good coding agent harness and the right collection of tools – compilers and debuggers and linters and fuzzers and suchlike I don't trust any code produced by a model directly until I've seen the model run it
-
AI Security Risk: Curated AI Systems Vulnerable to Hacking
By
–
That's one of my great fear. Having curated AI, and connect to other tools with a hack.
-
LLMs Show Strong Capability for Complex C Code Reasoning
By
–
I would not have trusted LLMs with C code a year ago but today's models appear to be very good at reasoning through memory management and other tricky aspects That said I'm not enough of a C expert myself to credible evaluate what they're doing!
-
Uncensored Internet Access Threatens Authoritarian Information Control
By
–
The ability for independent orgs to access uncensored internet and leverage publicly available data to share with everyone and anyone freak the CCP out.
-
AI Protein Analysis Aids Rare Childhood Cancer Research
By
–
i'm just a father of a 11 year old boy who had a rare cancer, and all your work will help others scientists to cancel the cancer. Talking to the mrotein is one of the first steps.
-
Claude Code Auto Mode: Daily Feature Releases Continue
By
–
This is insane. They literally drop every freaking day. Today: Claude code auto mode. Permission decisions on your behalf.