Karpathy says Codex and Claude Code need user control over subagent roles and model choice
emollick · x · 2026-07-22
Andrej Karpathy says Codex and Claude Code need finer control over subagents
Andrej Karpathy points out a practical limitation in tools like Codex and Claude Code: users need more control over how orchestrator AIs configure their subagents.
His core point is that the human should be able to decide:
- whether a subagent should do research, writing, or user testing
- which model each subagent should use
Without that control, the system becomes “a router problem again” — meaning the orchestrator is still making too many hidden delegation decisions on the user’s behalf.
More from coding & agent
- Claude reportedly beats a black-box AI detector after about seven tries — zacharynado · 2026-07-22
- Antithesis adopts exe to run agents on real machines safely — davidcrawshaw · 2026-07-22
- Every says a $625-a-year membership added $9,000 in MRR in two days — danshipper · 2026-07-22
- ChatGPT Work and Codex now let builders ship and share prototypes with sign-in — gabrielchua · 2026-07-22
- Superwall Launches New CLI for ClickHouse Queries and Integration Review — JordanMorgan10 · 2026-07-22
- Managing 10+ Coding Sessions: Open Source Tool Fleet Released — dee_hw · 2026-07-22