Using Local Coding Agents

Sebastian Raschka · 27 Jun 2026 · magazine.sebastianraschka.com ↗

3 korrents from this piece

Sebastian Raschka 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
Proprietary AI services will become more restrictive over time, making open-weight alternatives valuable as a backup.

Their wordsproprietary services may become more restrictive over time, and it's maybe a good idea to be comfortable with open-weight alternatives as a backup.
Our reading
When an AI lab builds both a model and a coding harness, the model is optimized for that lab's own harness first.

Their wordsif an LLM developer also develops a coding harness, it is somewhat safe to assume that their model is optimized for their own harness first
Our reading
In coding agents, untrusted repositories should be treated as hostile by default because they can steer the agent into risky actions via approved tools.

Their wordsuntrusted repos should be treated as hostile by default because they can steer the agent toward reading files, running commands, or sending data through approved tools.