Maanan Purothi
2 followers · 18 following · 32 views
on the atlas — 20
- Labs’ current alignment plans seem terrible — LessWrong3 savers
- Current alignment techniques might be ineffective (and actively bad) in the age of RL — LessWrong3 savers
- Frog and Toad and the Increasingly Capable Machines4 savers
- Research Lessons I Learned at MATS & Redwood — LessWrong11 savers
- The Economics of Transformative AI — LessWrong3 savers
- Four LLM loss functions → four flavors of LLM misalignment — LessWrong4 savers
- AI models may be capable of self-replicating without access to a datacenter \ Anthropic6 savers
- We've saved the world before: what the ozone hole teaches us about AI — LessWrong3 savers
- Taste for Makers10 savers
- On becoming competitive when joining a new company | Ludwig20 savers
- Your Goal Isn’t Really to Get a Job - by Matt Beard4 savers
- Maybe you’re not Actually Trying - by Cate Hall6 savers
- Things You're Allowed To Do | Milan Cvitkovic7 savers
- Obvious advice10 savers
- Theory of Change (Aaron Swartz's Raw Thought)84 savers
- Salad days — LessWrong5 savers
- Strategic Taste8 savers
- I take antidepressants. You’re welcome — LessWrong1 savers
- Why can’t we have nice things? Like, specifically? — LessWrong1 savers
- Curius / Onboarding2667 savers