GEN-1.5 training for 8+ months shows continuous metric gains via compounding algorithmic advances
ATTlKA · x · 2026-08-21
GeneralistAI reports that their GEN-1.5 model has been training continuously for over 8 months, with all tracked metrics showing consistent improvement. The gains are attributed to more efficient scaling, greater data absorption, post-training boosts, and compounding step-change improvements from algorithmic advances.
More from Research
- ShikharMurty: Pass@k gains may just sharpen distribution — ShikharMurty · 2026-08-21
- FasterFASTA tool achieves 1.69 GB/s with multithreaded BGZ decoding — viglovikov · 2026-08-21
- Princeton Paper: Legal Search Benchmarks Fail in Practice, New Dataset Released — burkov · 2026-08-21
- MIT Paper Finds Deleting Artist Data Doesn't Stop AI Recreating Images — technollama · 2026-08-21
- New journal to adopt GEB board, questioning value of legacy publishers — Afinetheorem · 2026-08-21
- HarnessEval-W: An Agentic Benchmark for World Models Evaluation — 青稞AI · 2026-08-21