Story · Katelyn Lesse and Angela Jiang (Anthropic)
Tokens Should Have Jobs (Katelyn Lesse and Angela Jiang (Anthropic))
talk · Story page
Given the same fixed budget of roughly 600,000 tokens, an agent that only executed scored 76 on financial analysis tasks, and one that spent part of that budget asking a second agent for advice scored 89. The three jobs: advising, grading to a rubric, reading transcripts into memory.
In plain words
- In a test, artificial intelligence software did better at financial analysis when it could ask another program for advice.
- Both versions had the same allowance for processing text, but one used some of that allowance to get advice.
- The talk also proposes helpers that check answers against written standards or save lessons from earlier attempts.
- For teams building these tools, the result suggests that advice could improve answers within the same allowance for processing text.
Appeared in
- A shell beats a typed tool catalog, and agents barely report their work
Sep 16, 2026 · in the sections
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.