Experimental News Clipping Site

Tag: prompt-engineering

  • Simon Willison’s Weblog: Gemini 2.5 Models now support implicit caching

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/9/gemini-implicit-caching/#atom-everything Source: Simon Willison’s Weblog Title: Gemini 2.5 Models now support implicit caching Feedly Summary: Gemini 2.5 Models now support implicit caching I just spotted a cacheTokensDetails key in the token usage JSON while running a long chain of prompts against Gemini 2.5 Flash – despite not configuring caching myself: {“cachedContentTokenCount": 200658, "promptTokensDetails":…

  • Simon Willison’s Weblog: Quoting Claude’s system prompt

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/8/claudes-system-prompt/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Claude’s system prompt Feedly Summary: If asked to write poetry, Claude avoids using hackneyed imagery or metaphors or predictable rhyming schemes. — Claude’s system prompt, via Drew Breunig Tags: drew-breunig, prompt-engineering, anthropic, claude, generative-ai, ai, llms AI Summary and Description: Yes Summary: The text pertains to…

  • Simon Willison’s Weblog: Dummy’s Guide to Modern LLM Sampling

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/May/4/llm-sampling/#atom-everything Source: Simon Willison’s Weblog Title: Dummy’s Guide to Modern LLM Sampling Feedly Summary: Dummy’s Guide to Modern LLM Sampling This is an extremely useful, detailed set of explanations by @AlpinDale covering the various different sampling strategies used by modern LLMs. LLMs return a set of next-token probabilities for every token in their…

  • Simon Willison’s Weblog: A comparison of ChatGPT/GPT-4o’s previous and current system prompts

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/29/chatgpt-sycophancy-prompt/ Source: Simon Willison’s Weblog Title: A comparison of ChatGPT/GPT-4o’s previous and current system prompts Feedly Summary: A comparison of ChatGPT/GPT-4o’s previous and current system prompts GPT-4o’s recent update caused it to be way too sycophantic and disingenuously praise anything the user said. OpenAI’s Aidan McLaughlin: last night we rolled out our first…

  • Simon Willison’s Weblog: Exploring Promptfoo via Dave Guarino’s SNAP evals

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/24/exploring-promptfoo/#atom-everything Source: Simon Willison’s Weblog Title: Exploring Promptfoo via Dave Guarino’s SNAP evals Feedly Summary: I used part three (here’s parts one and two) of Dave Guarino’s series on evaluating how well LLMs can answer questions about SNAP (aka food stamps) as an excuse to explore Promptfoo, an LLM eval tool. SNAP (Supplemental…

  • Simon Willison’s Weblog: An LLM Query Understanding Service

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Apr/9/an-llm-query-understanding-service/#atom-everything Source: Simon Willison’s Weblog Title: An LLM Query Understanding Service Feedly Summary: An LLM Query Understanding Service Doug Turnbull recently wrote about how all search is structured now: Many times, even a small open source LLM will be able to turn a search query into reasonable structure at relatively low cost. In…

  • Simon Willison’s Weblog: debug-gym

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Mar/31/debug-gym/#atom-everything Source: Simon Willison’s Weblog Title: debug-gym Feedly Summary: debug-gym New paper and code from Microsoft Research that experiments with giving LLMs access to the Python debugger. They found that the best models could indeed improve their results by running pdb as a tool. They saw the best results overall from Claude 3.7…

  • Simon Willison’s Weblog: Function calling with Gemma

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Mar/26/function-calling-with-gemma/#atom-everything Source: Simon Willison’s Weblog Title: Function calling with Gemma Feedly Summary: Function calling with Gemma Google’s Gemma 3 model (the 27B variant is particularly capable, I’ve been trying it out via Ollama) supports function calling exclusively through prompt engineering. The official documentation describes two recommended prompts – both of them suggest that…

  • Simon Willison’s Weblog: The "think" tool: Enabling Claude to stop and think in complex tool use situations

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Mar/21/the-think-tool/#atom-everything Source: Simon Willison’s Weblog Title: The "think" tool: Enabling Claude to stop and think in complex tool use situations Feedly Summary: The “think" tool: Enabling Claude to stop and think in complex tool use situations Fascinating new prompt engineering trick from Anthropic. They use their standard tool calling mechanism to define a…