Eight more months of agents

David Crawshaw · 8 Feb 2026 · crawshaw.io ↗

3 korrents from this piece

David Crawshaw did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
Local AI models will eventually catch up to frontier models once frontier progress hits diminishing returns.

Their wordsAt some point frontier models will face diminishing returns, local models will catch up, and we will be done being beholden to frontier models.
Our reading
Most current software and ways of solving problems are structured the wrong way for the agent era.

Their wordsMost software is the wrong shape now. Most of the ways we try to solve problems are the wrong shape.
Our reading
The best software design for an AI agent to use is the same as the best design for a human programmer.

Their wordsthe best software for an agent is whatever is best for a programmer.