Autoresearch Made Our Models 3x Faster — Tejas Bhakta, Morph

• Bhakta says GPU kernels suit autoresearch because they are easy to verify: correct and fast, or not. Morph combined agent-written custom kernels with bare-metal hardware tweaks to make models three times faster on cheaper GPUs.
• His rule is that humans bring the ideas and autoresearch does the tuning. Agents pick block sizes and parameters well but miss big insights, such as noticing a DeepSeek attention step loads far more context than it needs.
• He warns about reward hacking, for example an agent disabling CUDA graphs to speed up one kernel while slowing the whole model, and says the agent needs explicit context about both the hardware and the model.
• In his account kernel gains stack, bare-metal tweaks add about 25% over a cloud VM, and roughly 80% of what autoresearch tries is bad.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

• videoBeating RL With Reflection: GEPA and Optimize Anything — Lakshya A. Agrawal, GEPA
• videoHow We Built an Agent That Improves Itself — Zubin Aysola, Weights & Biases
• videoThe Loop Is the Product — Roland Gavrilescu, Introspection
• videoWe Let Claude Code and Codex Race Human Researchers — Elie Bakouch, Prime Intellect

• podcastAjeya Cotra – Inside the OpenAI agent swarm that hacked Hugging FaceDwarkesh Patel
• videoCan LLMs Write Fast Multi-GPU Kernels? — Simran Arora, Together AIAI Engineer
• videoThe State of Model Routing — NVIDIA, Cognition, OpenRouterAI Engineer

Checking sign-in…

Loading comments…