Tags → #llm
-
Agents will flop, delegation will rise
There is a lot of shit that can go wrong with agentic AI. But I expect that delegation will become more prevalanet with 'test-time-compute'.
-
(Draft) Testing AI Preferences
Testing LLM preferences is 80% methodology, 20% benchmarks, and 100% trust issues.
-
Agent Definition
Agents are now a marketing term, so how are we going to make it useful again?