PinnedPublished inTowards AIDSPy: Machine Learning Attitude Towards LLM PromptingTransition from prompt string manipulations to a PyTorch like frameworkNov 83Nov 83
PinnedPublished inTowards AIBuilding Confidence in LLM Evaluation: My Experience Testing DeepEval on an Open Datasetdeepeval helped me uncover what is the real source of Beyonce’s depressionOct 26Oct 26
PinnedPublished inHacking AIA scalable Zero shot intent classifierFlan-T5-Base as a fine tuned general classifierApr 17Apr 17
PinnedPublished inTowards AIPhilosophy of an Experimentation System — MLOPs IntroWhat project structure suits data-science “experiments”?Apr 28, 2023Apr 28, 2023
Published inHacking AIComponents that optimize n-shot text classificationN-shot classification options that don’t include an LLMAug 30Aug 30
Published inHacking AIHacking AI ManifestoThe underlying truth is that people are capable of achieving amazing things.Apr 23Apr 23
Published inTowards AIMLOps Without MagicSimple, Effective, and Maintainable.Aug 18, 2023Aug 18, 2023