For some time, I’ve argued that a common conception of AI is misguided. This is the idea that AI systems like large language and vision models are individual intelligent agents, analogous to human agents. Instead, I’ve argued that these models are “cultural technologies” like writing, print, pictures, libraries, internet search engines, and Wikipedia.

Hello and welcome to my new blog post. Today I am going to discuss a future threat which is invisible. With greater power comes greater…

Converts ASCII Prompts to Unicode Generating “Invisible” Prompts - Unighost_Prompt_Injection.py

Learn about invisible prompt injection, which is a silent threat to secure AI.

Payloads All The Things, a list of useful payloads and bypasses for Web Application Security

Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains how it is like SQL Injection...

GitHub Gist: instantly share code, notes, and snippets.

A detailed walkthrough of my current workflow for using LLms to build software, from brainstorming through planning and execution.

Tom Gally is a [professional translator](https://gally.net/translation.html) who has been exploring the use of LLMs since the release of GPT-4. In this Hacker News comment he shares a detailed workflow for …

OpenAI just started rolling out [Scheduled tasks in ChatGPT](https://help.openai.com/en/articles/10291617-scheduled-tasks-in-chatgpt), a new feature where you can say things like "Remind me to write the tests in five minutes" and ChatGPT will …

Most coders want AI to write code faster: I want AI to write FASTER CODE.

Refine your prompts

Contribute to 2-fly-4-ai/V0-system-prompt development by creating an account on GitHub.

Don't make this hard

Two big announcements from Anthropic today: a new Claude 3.5 Sonnet model and a new API mode that they are calling computer use. (They also pre-announced 3.5 Haiku, but that’s …

Anthropic has published the system prompts for Claude, its family of generative AI models. They instruct the model how it should -- and shouldn't -- behave.

Interesting tips here from Anthropic's documentation about how to best prompt Claude to work with longer documents. **Put longform data at the top**: Place your long documents and inputs …

Matt Webb's [Braggoscope](https://www.braggoscope.com/) ([previously](https://simonwillison.net/2023/Feb/13/braggoscope/)) is an alternative way to browse the archive's of the BBC's long-running radio series [In Our Time](https://www.bbc.co.uk/programmes/b006qykl), including the ability to browse by Dewey Decimal library …

There are many prompt writing tutorials available. In this one, I share unique insights not found elsewhere.

I’m beginning to suspect that one of the most common misconceptions about LLMs such as ChatGPT involves how “training” works. A common complaint I see about these tools is that …

Learn how to harness the power of ChatGPT and use advanced brainstorming techniques to think up new ideas or solutions to existing

Conditional Instructions open a powerful way for adversaries to target individual and delay detonation of malicious payloads for when certain conditions are met

An adversary can hide text in plain sight using the Unicode Tags. Using ASCII Smuggler you can encode and deocde such hidden messages

Hidden Prompt Injections with Anthropic Claude

The most advanced and complete catalog of 4000+ Midjourney AI styles: Artists, Techniques, Artistic Movements + Genres, Titles. Pulic domain styles. Style samples in V5 (5.1, 5.2), V4, and niji 5

leaked prompts of GPTs. Contribute to linexjlin/GPTs development by creating an account on GitHub.

Politeness and emphasis play a surprising role in AI-model communications.