Social Twitter Apr 28
If you don't understand this, you will not understand why LLM-based agents are irreparably failing f...
By @burkov
88 score
AI Analysis
Burkov's viral post arguing that LLM-based agents are fundamentally flawed for general-purpose problem solving because LLMs optimize next-token prediction, not expected utility maximization. They simulate the appearance of rational agency without actually being rational agents — lacking stable preferences, calibrated beliefs, and causal world models.
If you don't understand this, you will not understand why LLM-based agents are irreparably failing for a general-purpose problem solving.
An agent (by the way it was the topic of my PhD 20 years ago) to be useful, must be rational. Being rational means to always prefer an outcome that results in the maximal expected utility to its master/user.
Let’s say an agent has two actions they can execute in an environment: a_1 and a_2.
If the agent can predict that a_1 gives its user an expected utilit
llm-limitationsai-agentsrationalityexpected-utilityai-hype-critique