kalomaze: spiky capabilities aren't about verifiability — you can almost always manufacture information asymmetry
kalomaze · x · 2026-09-12
kalomaze pushes back on the popular intuition that spiky capabilities are a function of how verifiable a domain is (i.e., non-math/non-SWE domains won't fall to RLVR). He argues the general primitive is information asymmetry — and you can almost always manufacture it, so hard-to-verify domains aren't off-limits to RLVR.
More from AGI Musings
- Skimming Anthropic's S-1: Winner-Take-All Not of a Category, but the Whole Software Ecosystem — mobileraj · 2026-10-31
- "Claude only feels pain on Trainium" meme points to a digital minds essay — maxisawesome538 · 2026-10-31
- CS312 course post explains sharpness and the edge of stability in LLM pretraining — tatsu_hashimoto · 2026-10-31
- NBER paper: training your AI replacement can actually raise workers' pay — joshgans · 2026-10-31
- Trata's Hedge-Bench: no model tops 50% on real-world financial forecasting — ycombinator · 2026-10-31
- Anthropic's internal Claude model claims 2^o(n) 3-SAT algorithm, purportedly refuting the ETH — ctjlewis · 2026-10-31