FM News
Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing
On a story from Import AI3mo ago
Read the original at importai.substack.com
Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing
fmode.me/n/import-ai-460-reward-hacking-society-rsi-data-from-anthropic-and-rl-based-quadcopter-racing
More from FM News
Kubernetes just formed a workload conformance group. Here’s why it matters for AI teams.1 pts · The New StackThe Pulse: Anthropic kills the coding interview1 pts · The Pragmatic EngineerGPT-6.1 Terra vs. GPT-6 Astra: One sacrifices accuracy for lower cost and higher speed at high effort1 pts · The New StackDoorDash said it’s only received ‘several hundred’ orders from AI agents1 pts · TechCrunch AI