Claude Code Could 'Work 10 Whole Minutes' a Year Ago — Look How Far It's Come
majidmanzarpour · x · 2026-10-09
majidmanzarpour digs up his own 16-month-old post praising Claude Code for working uninterrupted on a complex feature 'for 10+ minutes' — then proof of its reliability, now a punchline. A neat yardstick for how much agent long-run autonomy has improved in just over a year.
More from coding & agent
- Swapping harness lifts GPT-5.6 repo migration from 6.5% to 31%, paper finds — omarsar0 · 2026-10-09
- Developer builds wildfire analysis tool with Opus 5.5: fire progression and hot spot tracking — natesiggard · 2026-10-09
- Subagent-as-a-service: betting on 'expert' agents like Harvey as tool calls for vertical AI — nbaschez · 2026-10-09
- WebMCP Debate: LLM Agents Skip Ads, Putting Ad-Based Business Models at Risk — ConnectRub4818 · 2026-10-09
- At first Grok Bot Meetup, audience-voted idea becomes a 139-marker map app in ~10 minutes — pswider · 2026-10-09
- Amazon AGI Lab: Why 80% Reliable Agents Still Break in Production — AI Engineer · 2026-10-09