system_prompts_leaks/claude.txt at main · asgeirtj/system_prompts_leaks
Contribute to asgeirtj/system_prompts_leaks development by creating an account on GitHub.
Claude’s System Prompt: Chatbots Are More Than Just Models
A couple days ago, Ásgeir Thor Johnson convinced Claude to give up its system prompt. The prompt is a good reminder that chatbots are more than just their model. They’re tools and instructions that accrue and are honed, through user feedback and design.
KoljaB/RealtimeVoiceChat: Have a natural, spoken conversation with AI!
Have a natural, spoken conversation with AI! Contribute to KoljaB/RealtimeVoiceChat development by creating an account on GitHub.
aperoc/toolkami: Minimal AI agent framework that just works with only seven tools.
Minimal AI agent framework that just works with only seven tools. - aperoc/toolkami
Gemma 3 QAT Models
Interesting release from Google, as a follow-up [to Gemma 3](https://simonwillison.net/2025/Mar/12/gemma-3/) from last month: To make Gemma 3 even more accessible, we are announcing new versions optimized with Quantization-Aware Training …
mims-harvard/TDC: Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science
Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science - mims-harvard/TDC
Beyond Text: Equipping Your Open WebUI AI with Action Tools
Give local LLMs superpowers with Open WebUI Tools. Use & build tools for function calling, API access (email/calendar) & real actions.
asgeirtj/system_prompts_leaks
Contribute to asgeirtj/system_prompts_leaks development by creating an account on GitHub.
huggingface/nanoVLM: The simplest, fastest repository for training/finetuning small-sized VLMs.
The simplest, fastest repository for training/finetuning small-sized VLMs. - huggingface/nanoVLM
Allowing CORS to local Ollama
Open AI Ollama Catalyst
A.I. Mistakes Are Way Weirder Than Human Mistakes – Pixel Envy
Last week, I published some thoughts on Meta’s eventual repositioning as a kind of television channel stocked with generated material for any given user: Then TikTok came around and did away with two expectations: that you should have to work to figure out what you want to be entertained by, and that your best source […]
Anemll/Anemll: Artificial Neural Engine Machine Learning Library
Artificial Neural Engine Machine Learning Library. Contribute to Anemll/Anemll development by creating an account on GitHub.
.jpg?width=92&height=&ar=&mode=&format=avif&dpr=2)
Dario Amodei — The Urgency of Interpretability
Reaction Prediction Models: Chapter 1 – Catalysts
In this chapter we will explore models that can propose and rank catalysts for a given reaction transform. The methodology uses graph-based deep learning models trained on a moderate sized corpus o…
I'd rather read the prompt
I have literally never seen LLM writing that actually improved my life.
Token Price Calculator
Claude generated by Simon Willison
Localforge – Offline AI Coding Agent (MIT-licensed) | Localforge
Run GPT-4-level code edits locally. 100% offline. MIT licensed.
Running Qwen3 on your macbook, using MLX, to vibe code for free
Learn how to run Qwen3 models locally on your Mac with MLX and create an autonomous coding agent using Localforge - completely free!
Suno | AI Music
Create stunning original music in seconds using AI. Make your own masterpieces, share with friends, and discover music from artists worldwide.
Model Context Protocol Untrusted Servers & Confused Clients, Plus a Sneaky Exploit
Model Context Protocol -- Exploits, Risks and Mitigations
Why I stopped Using Cursor and Reverted to VSCode
Is GitHub Copilot the best AI-assistant for Data Scientists?
humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents
Using LLMs as the first line of support in Open Source
Using LLMs as the first line of support in Open Source
From reading the title I was nervous that this might involve automating the initial response to a user support query in an issue tracker with an LLM, but Carlton Gibson …
An Increasingly Worse Response – Garrick van Buren
Cotypist – AI Autocomplete for Mac | Type Faster, Write Better
Cotypist: AI autocomplete for Mac. Type as fast as you think in any app. Save hours, reduce errors, and boost your productivity.
PhialsBasement/Chain-of-Recursive-Thoughts: I made my AI think harder by making it argue with itself repeatedly. It works stupidly well.
I made my AI think harder by making it argue with itself repeatedly. It works stupidly well. - PhialsBasement/Chain-of-Recursive-Thoughts
Where Do Scientists Think This Is All Going? | Quanta Magazine
We asked some of the world’s foremost experts an impossible question. Amazingly, they answered.
Daily jailbreak
#features