Author
Antoine Buteau

Antoine Buteau

Agent Coding Costs Hide in Review, Not Generation

A study of ChatDev traces finds that agentic coding systems spend most tokens on review and repeated context passing, not initial code generation.

Agents Change Work by Lowering the Cost of Execution

A Perplexity field study compares conversational search with autonomous agent execution and finds large time savings, lower dissatisfaction, and broader task scope.

Synthetic Consumers Work Better When They Talk First

A consumer research paper finds that LLMs can match human purchase-intent surveys when they answer in free text before being mapped back to Likert ratings.

AGI May Be a Phase, Not the Finish Line

A DeepMind report argues that human-level AGI may be followed by several pathways toward superintelligence, each constrained by data, compute, embodiment, and coordination bottlenecks.

Post-Training Is Where Models Learn Bad Habits

A post-training paper shows how interpretability tools can audit preference data, expose unwanted learning signals, and reshape rewards before models absorb bad habits.

Daily Digest - 2026-06-11

1. The Anatomy of a Reliable AI Agent — J.B. Why read: A framework for shifting from simple prompting to building system level harnesses for AI agents...

Lessons from Alex Sacerdote

Alex Sacerdote is the founder and portfolio manager of Whale Rock Capital Management, a TMT focused hedge fund managing over $8 billion in assets. Known...

Agent Harnesses Can Learn From Their Own Failures

Self-Harness shows that agents can use execution traces, targeted edits, and regression tests to improve the scaffolding around their own model.
You've successfully subscribed to Antoine Buteau
Great! Next, complete checkout to get full access to all premium content.
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.