delegating: which model, and why cheapest alone is wrong

haiku for mechanical, sonnet by default, opus only when the work still
holds a decision — which usually means the brief needs finishing rather
than a bigger model writing it.

and the part that matters: cheapness is a property of the pair, not the
model. a cheap model on a vague brief is the most expensive option
available — it returns something plausible, you reject it, you write the
brief you should have written, and you pay for the round twice.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Officer-Session: 656f5c85-e49a-4f1f-b9f3-042a04b4d043
This commit is contained in:
2026-08-25 03:50:49 +00:00
co-authored by Claude Opus 5
parent 606e332305
commit f0a5086dbc
+22
View File
@@ -44,6 +44,28 @@ An agent that has to ask a question has already cost more than it saved. So the
Run it in the background and carry on. A brief good enough to run unattended is the same brief that makes
the result reviewable.
# Choosing the model
**The cheapest one that will get it right.** Not the cheapest one; the cheapest one that will get it
right, which is a different question and has to be asked per task.
- **Haiku** — mechanical and high-volume with no judgement in it. A rename across forty call sites, a
JSON transform, moving a block of files to a new shape.
- **Sonnet** — the default, and what most of this work is. A feature whose design is settled and whose
brief names the files: translations, a form, tests for a rule already agreed, a migration over a list.
- **Opus** — when the work still contains a decision. Which usually means the brief is incomplete, so
the first move is to finish the brief rather than to spend more per token on writing it.
## Cheapness is a property of the pair, not the model
A cheap model on a vague brief is the most expensive option available: it returns something plausible,
you review it, you reject it, you write the brief you should have written, and you pay for the whole
round twice. The saving comes from the brief being good enough that a smaller model cannot go wrong —
so if you find yourself reaching for a bigger model to compensate for a thin brief, fix the brief.
The other direction is real too, and cheaper to correct: a task that comes back wrong from Haiku goes to
Sonnet and costs one wasted run. Start low.
# Reviewing what comes back
**Read the diff, not the summary.** The summary is written by the thing being reviewed. `git diff` is not.