BS metric... /s
Re:2025: The Year in LLMs
by jennyholzer3 on Friday January 02, 2026 @09:20AM
(#46464980)
Chat GPT told him it was true
Re:2025: The Year in LLMs
by aspenmartin on Friday January 02, 2026 @04:08PM
(#46469358)
- Scaling laws (Chinchilla type)
- METR task horizon
It's a mix, performance gains are bursty but we have been getting a lot of bursts (RLVR, test-time compute, agentic breakthroughs)
By what metric?