AI, Work and the Economy

Latest/Story

Measuring what AI can do

Two items, from 23 Oct 2026 to 29 Oct 2026, oldest first.

See also: Point 1 of our view: AI does more office work, cheaper

AI and technologyNew data

Epoch (23 Oct): six frontier models try 11 of its research tasks unaided; none reliably meets its quality bar

Epoch AI had six leading models attempt 11 realistic tasks from its own work, one try each with no help: Claude Fable 5.1 and GPT-6 Astra tied for first, but none reliably met Epoch's standard, doing well on coding and data analysis and poorly on experiment design and interpretation. Its index puts Gemini 4 Argon at 166, behind Opus 5.5 and GPT-6 Astra at 169.

Why it matters. A careful test by a research group finds that today's best AI models can do its well-defined tasks but cannot yet reliably do its open-ended research work unaided. If this holds more widely, replacing skilled workers outright might take longer than the recent wave of job-cut announcements suggests, even as routine parts of their work are automated.

Next. The next published measures of how long and how open-ended a task AI can complete on its own.

Sources: epochai.substack.com · Point 1 of our view

AI and technologyNew dataUpdate

Surge AI's Dayjob: Tax (27 Oct): best agent completes 10.8% of 50 professional tax assignments to a 95% bar

Surge AI tested AI agents on 50 end-to-end tax engagements across eight areas of practice, with 1,789 workspace files (median 30 per assignment). Claude Sonnet 5.5 passed 10.8%, Fable 5.1 9.6% and Opus 5.5 9.2% at the first attempt; agents missed issues clients did not raise, such as a filing deadline or a marital status.

Why it matters. On fifty realistic tax engagements, the best AI agent finished about one in ten to a professional standard, often missing issues a client had not raised. Pieces of such work are clearly within reach of machines, but on this evidence end-to-end replacement of skilled tax advisers is not yet close.

Next. Results for newer models on the same assignments, and November's figures on job cuts attributed to AI.

Sources: surgehq.ai, news.ycombinator.com · Point 1 of our view