Every Team to Live-Test Astra 6.2 and Sol 6.2, Inviting Developer Scrutiny On-Stream
danshipper · x · 2026-11-18
Every's frontier team will live-test the new Astra 6.2 and Sol 6.2 models at 3 PM ET, inviting OpenAI's Thibault Sottiaux to join and spot what they miss. The goal is publicly mapping where each new model shines (and doesn't), while showing their evaluation process to viewers who can share observations and ask questions.
Related event: Every's Frontier Team to Livestream Tests of OpenAI's Astra 6.2 and Sol 6.2(2 posts)→
More from Models
- LLMs excel at convergent thinking but suck at divergent thinking — ergestx · 2026-11-19
- Frontier agents report significant findings up to 98% of the time on null-effect data — RexDouglass · 2026-11-19
- Grok Build tops HF Harness Leaderboard in all four configs but fails on text-only models — TheZachMueller · 2026-11-18
- OpenAI retakes MathArena top spot as GPT-6.2 Astra hits 79.25% on ArXivLean — sandersted · 2026-11-18
- GPT-6.2 tops browser-use benchmark: 82% success, 35% cheaper, 2x faster — gdb · 2026-11-18
- LMArena: Meta's Muse Ember is 13x faster and ~3x cheaper than GPT-6 Luna and Claude Haiku 5.5 — arena · 2026-11-18