SSHaven't heard of that, will check it out.Reply·Article·Jul 1·Where AI Agents Belong in Data Engineering: The Correctness Layer
SSLLMs for brainstorming, ideas, but not for correctness, indeed.Reply·Article·Jul 1·Where AI Agents Belong in Data Engineering: The Correctness Layer
SSevery probabilistic decision should eventually terminate in something deterministic. 100%. Yes thinker layers, or what the article suggests, that you are not dependend on model must be the goal, so you can exchange the models, as the model uses a deterministic tool like a linter or compiler.Reply·Article·Jun 30·1·Where AI Agents Belong in Data Engineering: The Correctness Layer
SSThanks man!Reply·Article·Jun 30·1·Where AI Agents Belong in Data Engineering: The Correctness Layer