Tokens Should Have Jobs — Katelyn Lesse & Angela Jiang, Anthropic

Researchers from Anthropic show that giving AI agents larger token budgets (tokens are the building blocks of AI responses) isn't always the answer.

With a fixed budget of 600,000 tokens, an agent that only executed tasks performed worse than one that used tokens more strategically: by consulting an adviser, by having a grader review results iteratively, or by having the agent study its own previous attempts. For financial analysis, an answer that is 80 percent correct often isn't useful — one wrong figure ruins the whole result. A simple execution succeeded in only 42 percent of tests on the first try, costing roughly 1.8 million tokens total. Smarter strategies could reach the same quality with fewer tokens.

More to read

Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation

Techmeme · 3 h ago

DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions

Techmeme · 4 h ago

Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash

Techmeme · 4 h ago

One word for AI agents in 2027

Nate Herk · 8 h ago