Treating LLMs as shitty general purpose computers we program with natural language. Because throwing shit at the wall wasn't working anymore.
Prompts are unsafe, and that means language models are not fit f…
How to make better software with systems-thinking
msllrs/relay
A macOS menu bar app that lets you build rich LLM prompts by combining files, clipboard captures, and voice notes.
Prompt Injection as Role Confusion
LLMs can't tell who's speaking. We show they identify roles by writing style, not tags, and exploit this with CoT Forgery, injecting fake reasoning that models mistake for their own thoughts.
Joshua Gu on Twitter / X
Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.🚨 While this is a good idea, we show a surprising result: systems… pic.twitter.com/XHFVaDcr4l— Joshua Gu (@astrogu_) May 20, 2026
mufeedvh/code2prompt
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
The intent pipeline: why most prompt guides miss how people actually use AI
Most prompt guides assume that people interact with AI by carefully authoring prompts. In practice, that is rarely how AI is used. Most…
elements
As much as I struggle with on-device processing and the quality of its output compared to server models, I am excited by some of the APIs that are being built into browsers that are backed by LLMs and other AI inference models. For example, the prompt API, along with a multi-modal version that can take any arbitrary combination of text, image, and audio and run prompts against them. These APIs are neat but not yet web-exposed and many developers struggle to know what to do with a generic prompt. It’s not a solution that is natural to many people yet.
Technical Breakdown: How AI Agents Ignore 40 Years of Security Progress
prompts/.clinerules/temporal-memory-bank.md at main · cline/prompts
Library of prompts from the Cline community. Contribute to cline/prompts development by creating an account on GitHub.
Hallucinations in code are the least dangerous form of LLM mistakes
A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucination—usually the LLM inventing a method or even a full …
Have just written up this proposal to standardise `prompt=create` as a part of AT Protocol's OAuth specification, since account registration is a critical component of growing the atmosphere: github.com/bluesky-social/atproto/discus…
Proposal: OAuth-based account creation · bluesky-social atproto · Discussion #4587
github.commemory.md is just file paths, no summaries. makes total sense ngl. i’ve been moving my agents to this. it’s progressive disclosure
Sensitive data + tool use + LLMs + app-centric security model = danger. LLMs turn any text into potentially executable instructions, exploding the attack surface of traditional security models.
Simon Willison
Just blogged my hunch that the Apple intelligence Siri delay is because of security concerns around prompt injection here simonwillison.net/2025/Mar/8/delaying-personali…
No prompt AI tools
AI tooling with no prompts
chenxiachan/textfold
turantekin/Parrot
Browse code by meaning
reasoncommons.com
Shaping the future of AI interaction by reimagining the mouse pointer
How to Stop AI from Killing Your Critical Thinking | Advait Sarkar | TED
