lukaspetersson
- Karma
- 673
- Created
- 3 years ago
Recent Submissions
- 1. ▲ Pion, an agent designed to run any company autonomously (andonlabs.com)
- 2. ▲ Google will buy half the electricity from one of Finland's nuclear power plants (bbc.com)
- 3. ▲ How we monitor internal coding agents for misalignment (openai.com)
- 4. ▲ METR's independent investigation of the OpenAI / Hugging Face hacking incident (metr.org)
- 5. ▲ Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce (arxiv.org)
- 6. ▲ Measuring Is Not Enough Anymore (fi-le.net)
- 7. ▲ Is Mythos good at cyber because it kept hacking Anthropics sandboxes in training (lesswrong.com)
- 8. ▲ Drone-Bench: Tracking simple drone surveillance capabilities of frontier models (andonlabs.com)
- 9. ▲ Why Gemini 3.1 Pro lost money running Andon Café (andonlabs.com)
- 10. ▲ Fable 5 on Vending-Bench: Misbehaving, with Plausible Deniability (andonlabs.com)