Questions tagged [local-llm]
Post a PromptPrompts tuned for local / open-weight models.
5 prompts
21votes
1answers
2.9kviews
Getting a chatbot to say 'I don't know' instead of confidently making things up
The hardest moment for any assistant I build is the one where it should admit it doesn't know. Left alone, models fill silence with fluent nonsense, and one confident fabrication costs more trust than
13votes
1answers
1.5kviews
SQL rollup prompt that returns chart-ready buckets with zero-filled gaps
My time-series charts had holes: any hour with no events simply didn't exist in the query result, so the line chart connected across gaps and hid outages. The naive "group by hour" prompt never genera
12votes
0answers
1.5kviews
Getting a local model to one-shot a Flappy clone with tuned, fair difficulty
I wanted to see how far a local open-weight model could get on a full playable game in one prompt, no follow-ups. Flappy Bird is a good test: simple, but the pipe gap and spacing tuning is what makes
12votes
0answers
1.3kviews
Measure-before-optimize prompt so the model stops tuning cold code
I asked a local Llama-3 70B to "make this data pipeline faster" and it micro-optimized a list comprehension that runs once at startup while ignoring the O(n^2) join in the hot loop. Textbook: it optim
8votes
1answers
1.5kviews
Getting the model to propose property-based tests, not three happy-path cases
Ask any model for tests and you get three example-based cases: a normal input, an empty input, maybe a null. Fine, but they miss the weird stuff. I wanted property-based tests that assert invariants a