basforge

Search titles, text and the “If it doesn’t work” cases.

    RU
    Topic · AI

    Prompts

    How to ask, keep a conversation going and check the answer

    Entries
    13 + 2
    Cases
    7
    Updated
    2026-10-19

    Tips

    11
    A big task: questions and a plan first, then the workBefore a big task, ask the model not to act but to ask what’s missing and propose a plan.A rule in a prompt gets a reason instead of capsA newer model executes “NEVER change the ports” literally and more broadly than needed.Consistent answers come from format and checks, not temperature 0A model picks the next token with some randomness, so one question gives different wordings.Long document first, question last, answer with quotesPut a document of dozens of pages at the start of the prompt and the question after it, and ask the model first to write out the quotes its answer relies on.Match reasoning to the task: an effort level instead of “think harder”Set reasoning depth with the effort level, not with words in the prompt: low for translation, extraction and chat, high and up for bug hunting, architecture and tasks whose answer can be checked.Need a particular kind of answer? Show an example instead of describing itOne example of the answer you want sets length, tone, detail and format more precisely than a paragraph of description.New task, new chatA conversation about Traefik, then backups, then an email to a colleague, all in one chat, is a context where every new task drags the tails of the earlier ones along: other files, cancelled decisions, tone.Put the date, versions and environment in the promptThe model doesn’t know today’s date, which version of a program you have, or what came out after its knowledge cutoff.Review in a new chat, without your version, asking for mistakesA model tends to agree: in the same chat where it wrote the answer, or where you praised it, a review will confirm it.Which language to prompt in: non-English costs more tokens, not more misunderstandingThe same text in Russian takes 1.16 times as many tokens as in English on the o200k_base vocabulary; on the 2023 vocabulary it was 1.64 times.Wrong answer? Edit your question instead of arguing with the answerIf an answer went the wrong way, edit the original message and resend it instead of writing “no, not like that” as the next turn.

    Also on this topic

    Entries from other topics that are about this too.