[llmslave2]

> But the capabilities of LLMs is clearly exponential and perhaps super exponential

By what metric?

[aspenmartin]

- 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)

[jennyholzer3]

Chat GPT told him it was true

[utopiah]

BS metric... /s