Meta's Muse: 100+ agent behaviors tracked with launch-blocking evals explain the 7-month gap
generativist · x · 2026-10-12
Citing Alexandr Wang, Hesamation explains why Meta spent 7 months on Muse after a 1-2 week prototype:
- 100+ specific agent behaviors tracked in a spreadsheet, each with its own eval and a launch-blocking threshold
- All 100 only went green with Muse Spark 1.3; fewer than 200 people across model + product
- The lesson from OpenClaw, which had magic moments but broke constantly: reliability IS the product
- Whether it holds up for millions of users is another story
More from coding & agent
- Sentry founder: complexity is in database and storage, not the language — zeeg · 2026-10-13
- User says Grok Bot researched and booked his entire Lisbon trip with one prompt — elonmusk · 2026-10-13
- GitHub Actions tip: always cache dependencies — pipelines cut from 20 min to 3 min — vboykis · 2026-10-13
- Grok Bot turns X bookmarks into a Notion second brain in this automated workflow — elonmusk · 2026-10-13
- Open-source Android app runs Codex CLI on your phone via proot, no root needed — 3amae404 · 2026-10-13
- User says Grok replaced his ChatGPT, Claude and Cursor workflows entirely — elonmusk · 2026-10-13