#5950.0AIT1 — official sourceCooling

Advancing science and engineering with Antigravity's /teamwork

Spotted 2026-11-15 02:08 (UTC+8) · original event 2026-11-13 · sources: Hacker News, Google Research Blog, Daily AI Brief · spreading on 3 platforms

Heat score

Rank score: 6040% — where it sits on the charts
Discussion score: 8040% — how much people are talking about it
Cross-platform score: 7020% — how many platforms it spread to
Composite heat score:50.0rank × 0.4 + discussion × 0.4 + cross-platform × 0.2 — includes a -20-point cooling decay (peak passed, attention fading).

Why it matters

Open research problems that take a PhD team months are still gated by human hours: one agent loop stalls, forgets context, or cannot check its own work, so hard problems stay stuck even when the model is smart enough.

The angle

Google's agent teams just proved a 2013 math conjecture and formalized the Weil conjectures: what /teamwork actually does, and why multi-agent critique beats one big modelSuggested format: Short video · for AI researchers, developers, math and science enthusiasts

Evidence chain

• HN #5, 77 pts/20 cmt (2026-11-15)• Google Research blog 2026-11-13 (Vahab Mirrokni): /teamwork multi-agent framework in Antigravity now open to external researchers and developers on Gemini 4 models, with results on open problems in mathematics, chemistry, systems software and ML engineering - Courtade-Kumar conjecture proved in full generality (Google, CUHK, USC, CMU), LEAP fully autonomously produced a machine-checked formalization of the Weil conjectures in Lean (about 1.8M lines, 28,800 subagent invocations), first formalizations of the Birkhoff conjecture (open since 1927) and the 3D Bochner-Riesz conjecture• 10,000 academic researchers offered six months of free access to the highest usage tier• Daily AI Brief 2026-11-14 and letsdatascience.com covered it• all work done with human experts per Google• 2026-11-15 03:07 update: HN #6, 93 pts/26 cmt• rank 90 -> 85• 2026-11-15 04:07 update: HN #8, 111 pts/28 cmt• discussion 60 -> 70• 2026-11-15 05:07 update: HN #8, 127 pts/31 cmt• score unchanged 76.0 (rank 85, discussion 70, cross 70)• 2026-11-15 06:07 update: HN #9, 138 pts/33 cmt• score unchanged 76.0 (rank 85, discussion 70, cross 70)• 2026-11-15 07:07 update: HN #11, 147 pts/34 cmt• rank 85 -> 75• 2026-11-15 08:07 update: HN #10, 154 pts/36 cmt• rank 75 -> 85• 2026-11-15 09:07 update: HN #11, 158 pts/36 cmt• rank 85 -> 75• 2026-11-15 10:07 update: HN #13, 168 pts/37 cmt• score unchanged 72.0 (rank 75, discussion 70, cross 70)• 2026-11-15 11:07 update: HN #14, 172 pts/39 cmt• score unchanged 72.0 (rank 75, discussion 70, cross 70)• 2026-11-15 12:07 update: HN #16, 177 pts/39 cmt• score unchanged 72.0 (rank 75, discussion 70, cross 70)• 2026-11-15 13:07 update: HN #21, 181 pts/39 cmt• rank 75 -> 60• 2026-11-15 14:07 update: HN #22, 188 pts/40 cmt• score unchanged 66.0 (rank 60, discussion 70, cross 70)• 2026-11-15 15:07 update: HN #21, 192 pts/40 cmt• score unchanged 66.0 (rank 60, discussion 70, cross 70)• 2026-11-15 16:07 update: HN #23, 193 pts/41 cmt• score unchanged 66.0 (rank 60, discussion 70, cross 70)• 2026-11-15 17:07 update: HN #25, 194 pts/42 cmt• score unchanged 66.0 (rank 60, discussion 70, cross 70)• 2026-11-15 18:07 update: HN #26, 199 pts/44 cmt• score unchanged 66.0 (rank 60, discussion 70, cross 70)• 2026-11-15 19:07 update: HN #28, 203 pts/47 cmt• score 66.0->70.0 (rank 60, discussion 70->80, cross 70)• 2026-11-15 20:07 update: HN #27, 204 pts/48 cmt• score unchanged 70.0 (rank 60, discussion 80, cross 70)• 2026-11-15 21:07 update: HN #26, 206 pts/49 cmt• score unchanged 70.0 (rank 60, discussion 80, cross 70)• 2026-11-15 22:07 update: dropped out of HN top 30• cooling -20 (70.0 -> 50.0)