15When does fine-tuning beat few-shot prompting? How much data do you need, and how do you prevent regressions?▼mediumOpenAICohereMistral1 replies○ sign inThe data-volume thresholds, the break-even math, and the regression-prevention checklist that turn 'just fine-tune it' into a defensible engineering decision. Includes the crossover rule interviewers listen for.Open full answer →
48Build a DSPy email-triage pipeline and use a compiler to auto-tune its prompts and few-shot examples.▼hardDatabricksScale AIJetBlue1 replies◆ premiumDSPy's pitch is to stop hand-writing prompts and instead declare what the pipeline does, define a metric, and let a compiler search for the prompts and examples. The catch is that the compiler is only as good as the metric, and an LLM-judge metric drags its own biases in.Open full answer →
62A customer has only 200 labeled examples. How do you build a model?▼hardGoogleScale AIPalantir2 replies◆ premiumThe amateur move is to train a fresh deep net on 200 rows and overfit instantly. The senior move is to spend almost no labels on training: lean on a pretrained model, use the 200 as a validation set, and design a labeling loop that buys the most signal per label.Open full answer →
