Author
Sam Q. writes terse, tested prompt recipes for PromptAttic. Ships them the way you would a commit message: short, verified, no preamble.
OpenAI prompt caching is implicit, so the failure mode is not a cache you never made, it is one you keep destroying. Four recipes, the request settings that void a prefix without touching your text, and the two token floors the vendors disagree on.
An LLM confidence score tells you how sure the model was. Which providers return logprobs in 2026, what to do on Claude which returns none, and 4 copy-paste recipes.
Five copy-paste Tree of Thoughts (ToT) prompt recipes for 2026: the one-prompt expert panel, branch-score-pick, explicit backtracking, ToT for planning, and when to skip ToT and just use self-consistency.
Four copy-paste logit_bias recipes for the OpenAI API in 2026: ban a token, pin a classifier, fix the tokenizer mismatch, and know when it is the wrong tool.
Prompt templates with {{variables}} in 2026: 5 copy-paste recipes for reusable, cacheable, injection-safe prompts on Claude and OpenAI, plus the failure modes that bite.
Streamed tool arguments arrive as partial_json fragments, not JSON. Four copy-paste recipes to buffer by index, parse once, and stop corrupting tool calls, on Claude and OpenAI.
frequency_penalty counts, presence_penalty flags. Four copy-paste recipes for when to grab which OpenAI sampling knob, plus the one config that quietly breaks your JSON.
tool_choice in 2026: four copy-paste recipes to force any tool, pin one named tool, forbid tools for a turn, or leave it on auto, in Claude and OpenAI, each with the failure mode that bites.
Self-consistency prompting in 2026: five copy-paste recipes that sample multiple reasoning paths and majority-vote the answer, plus a gate for when to skip it.
Four paste-ready generated knowledge prompting recipes for 2026: make the model generate facts first, then answer, each with the failure mode nobody prints.
Self-ask prompting in 2026: four copy-paste recipes that make a model ask and answer its own follow-up questions, plus the search-tool upgrade and the gate for when to skip it.
Chain of Verification (CoVe) is a four-step prompt that cuts hallucinations by making a model draft, plan verification questions, answer them independently, and rewrite keeping only what survived.
