3. Dynamic few shot prompting They cautioned against using traditional few shot prompting for agents. Seeing the same few examples repeatedly will cause the agent to overfit to these examples. Ex: if you ask the agent to process a batch of 20 resumes, and one example in the prompt visits the job description, the agent might visit the same job description 20 times for these 20 resumes. Their solution is to introduce small structured variations each time an example is used: different phrasing, minor noise in formatting, etc. [Translated from EN to English]
CODE
-
Tool Use in Agents: Managing Complexity and Forcing Tool Selection
By
–
2. Tool use Given how easy it is to add new tools (e.g., with MCP servers), the number of tools a user adds to an agent can explode. Too many tools make it easier for the agent to choose the wrong action, making them dumber. They caution against removing tools mid-iteration. Instead, you can force an agent to choose certain tools with response prefilling. Ex: starting your response with <|im_start|>assistant<tool_call>{"name": “browser_ forces the agent to choose a browser. Name your tools so that related tools have the same prefix. Eg: browser tools should start with `browser_`, and command line tools should start with `shell_`
-
Free LLM Tool Available Now at Datasette
By
–
I'm currently giving it away for free https://
llm.datasette.io -
Spark AI Documentation Site with System Prompt Details
By
–
Here's the unofficial documentation site I built with Spark itself, including a copy of the system prompt, details of the available tools and a page full of information about the Azure container environment Spark uses to run its own editor https://
github-spark-docs.simonwillison.net -
GitHub Spark: AI-powered React app platform with auth and storage
By
–
GitHub released Spark yesterday, their extremely well crafted prompt-to-app platform for creating and iterating on React apps with user auth and persistent storage I like it a lot! I reverse engineered it with Spark itself, the details are fascinating
-
Kimi K2 and Groq Create Dynamic Multiplication Circle Visualization
By
–
Kimi K2 @Kimi_Moonshot + @GroqInc vibe coding
— AK (@_akhaliq) 24 juillet 2025
animated visualization that plots a dynamic multiplication circle (a.k.a. times table circle) on a circle of 200 points. The connections should evolve over time as the multiplier increases. Add soft neon glow effects and smooth… pic.twitter.com/bPO3uW2WfIKimi K2 @Kimi_Moonshot + @GroqInc vibe coding animated visualization that plots a dynamic multiplication circle (a.k.a. times table circle) on a circle of 200 points. The connections should evolve over time as the multiplier increases. Add soft neon glow effects and smooth
-
Claude Sonnet 4 Custom Prompt Project Implementation
By
–
Claude Sonnet 4 with a custom prompt in a project
-
Kimi K2: Open-Source Trillion-Parameter MoE Model Released
By
–
Kimi K2 = Hype or Not?
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 24 juillet 2025
It is the first open‑source trillion‑parameter MoE model
• 1 T total / 32 B active parameters → giant yet efficient
• Outscores GPT‑4.1 & Claude‑4 (65.8 % SWE‑Bench, 53.7 % LiveCodeBench)
• 128 k context, MIT‑licensed, no vision implemented…… pic.twitter.com/tiouZDLCScKimi K2 = Hype or Not? It is the first open‑source trillion‑parameter MoE model • 1 T total / 32 B active parameters → giant yet efficient
• Outscores GPT‑4.1 & Claude‑4 (65.8 % SWE‑Bench, 53.7 % LiveCodeBench)
• 128 k context, MIT‑licensed, no vision implemented… -
Qwen3-Coder-480B Creates Lissajous Curve Visualization
By
–
Qwen3-Coder-480B-A35B @Alibaba_Qwen + @hyperbolic_labs vibe coding
— AK (@_akhaliq) 24 juillet 2025
Lissajous curve visualization pic.twitter.com/mInB9wMsvSQwen3-Coder-480B-A35B @Alibaba_Qwen + @hyperbolic_labs vibe coding Lissajous curve visualization
-
LLM Tool Logging Features in Datasette Platform
By
–
It's this feature of my LLM tool https://
llm.datasette.io/en/stable/logg
ing.html
…