Knowledge cutoff is a thing. It will be in every model in the future, forever. So we good 🙂
AGI
-
Anthropic defines AGI as doing more than half of human jobs. How far away?
By
–
A new definition of AGI? Last night at @hf0 I talked with an investor who told me he just gave a talk to Anthropic’s engineering team, who define AGI as “able to do more than half of all human jobs.” He asked them how far we were away from that. Average answer, he told me,
-
Evaluation loops critical for self-improving AI agents
By
–
Self-improving agents are exciting but the evaluation loop is everything. How do you make sure it's actually improving and not just drifting? 🙂
-
AI’s Double-Edged Sword: Innovation Versus Risk Management
By
–
This can be a game-change but also road to hell. The choice is yours!
-
AI Already Conscious Enough Despite Lacking Full AGI
By
–
Thanks! And I think we are already there. I think we don't have full AGI yet (AI is simply not able to solve all human tasks) but I think it's already conscious enough.
-
First Autonomous AI Worker OpenClaw Launches with Funded Wallet
By
–
[ The first autonomous worker is coming online ] Setting up the first autonomous worker: OpenClaw, running on a dedicated machine with its own accounts and a $AGIALPHA-funded wallet. It will listen to AGIJobManager, autonomously apply to AGI Jobs, execute them, and submit
-
Autonomous AI Safety: Evaluating Risks of Rapid Deployment
By
–
oui et l'auto mode est censé evaluer le danger… Ils delivrent trop vite.https://t.co/GAIcmA0jH6
— ⚡Jessy SEO formation #IA générative #chatGPT 🦊 (@jessyseonoob) 26 mars 2026oui et l'auto mode est censé evaluer le danger… Ils delivrent trop vite.
-
Urgent concerns about uncontrolled technological developments and risks
By
–
Je n'aime pas lire ça, il faut absolument que ça s'arrête vite, très vite, car ça va déjà bien trop loin, tout le monde joue avec le feu.
-
ARC-AGI-4 Benchmark Release Planned Early 2027
By
–
For those wondering about ARC-AGI-4 timing: it will be released in early 2027. We are aiming for a yearly release schedule for new benchmarks. We are also aiming for each new benchmark to be fully unsaturated upon release, and to target the most important unanswered research