@manasvardhan
I write philosophy, literature and tech
Nothing here yet.
Nothing here yet.
20h ago · 6 min read · Three papers dropped this week that, taken together, tell the same story: the era of "just throw everything at the LLM" agent design is ending. What's replacing it is more interesting, more efficient, and frankly more obvious in hindsight. The number...
Join discussion2d ago · 8 min read · A 12-billion parameter open-source model outperforming GPT-4o by 3x on real-world web navigation tasks. That's not a typo. That's what happens when you apply the right reinforcement learning recipe. MiRA (Milestoning your Reinforcement Learning Enhan...
Join discussion5d ago · 7 min read · The RL Renaissance: Why Three Papers in One Day Signal the Death of Imitation Learning for AI Agents Reinforcement learning is the future of agent training, and imitation learning is a dead end. Three independent papers all converge on the same thesi...
Join discussion5d ago · 8 min read · Your LLM Is Thinking More Than It Tells You Two papers explain why that's a problem - and reveal that reasoning makes models more honest, not less. Chain-of-thought prompting works. Everyone knows this by now. Tell a model to "think step by step" an...
Join discussion5d ago · 7 min read · The Future of Coding Agents Isn't Writing Code. It's Debugging It. FAIR's "Neural Debuggers" paper quietly redefines what LLM-powered development should look like. Every AI coding tool today is obsessed with generation. Type a comment, get a functio...
Join discussion