Simon Willison’s Weblog

Subscribe
Atom feed for llms

688 items tagged “llms”

Large Language Models (LLMs) are the class of technology behind generative text AI systems like OpenAI's ChatGPT, Google's Gemini and Anthropic's Claude.

2022

I Taught ChatGPT to Invent a Language (via) Dylan Black talks ChatGPT through the process of inventing a new language, with its own grammar. Really fun example of what happens when someone with a deep understanding of both the capabilities of language models and some other field (in this case linguistics) can achieve with an extended prompting session.

# 6th December 2022, 7:30 pm / gpt-3, generative-ai, openai, chatgpt, linguistics, prompt-engineering, llms

The primary problem is that while the answers which ChatGPT produces have a high rate of being incorrect, they typically look like they might be good and the answers are very easy to produce. There are also many people trying out ChatGPT to create answers, without the expertise or willingness to verify that the answer is correct prior to posting. Because such answers are so easy to produce, a large number of people are posting a lot of answers. The volume of these answers (thousands) and the fact that the answers often require a detailed read by someone with at least some subject matter expertise in order to determine that the answer is actually bad has effectively swamped our volunteer-based quality curation infrastructure.

StackOverflow Temporary policy: ChatGPT is banned

# 6th December 2022, 12:16 am / gpt-3, generative-ai, openai, chatgpt, stackoverflow, ai, llms

AI assisted learning: Learning Rust with ChatGPT, Copilot and Advent of Code

Visit AI assisted learning: Learning Rust with ChatGPT, Copilot and Advent of Code

I’m using this year’s Advent of Code to learn Rust—with the assistance of GitHub Copilot and OpenAI’s new ChatGPT.

[... 2,661 words]

Building A Virtual Machine inside ChatGPT (via) Jonas Degrave presents a remarkable example of a creative use of ChatGPT: he prompts it to behave as a if it was a Linux shell, then runs increasingly complex sequences of commands against it and gets back surprisingly realistic results. By the end of the article he’s getting it to hallucinate responses to curl API requests run against imagined API versions of itself.

# 5th December 2022, 1:43 am / openai, gpt-3, ai, generative-ai, chatgpt, llms

A new AI game: Give me ideas for crimes to do

Visit A new AI game: Give me ideas for crimes to do

Less than a week ago OpenAI unleashed ChatGPT on the world, and it kicked off what feels like a seismic shift in many people’s understand of the capabilities of large language models.

[... 1,069 words]

These kinds of biases aren’t so much a technical problem as a sociotechnical one; ML models try to approximate biases in their underlying datasets and, for some groups of people, some of these biases are offensive or harmful. That means in the coming years there will be endless political battles about what the ‘correct’ biases are for different models to display (or not display), and we can ultimately expect there to be as many approaches as there are distinct ideologies on the planet. I expect to move into a fractal ecosystem of models, and I expect model providers will ‘shapeshift’ a single model to display different biases depending on the market it is being deployed into. This will be extraordinarily messy.

Jack Clark

# 16th November 2022, 11:04 pm / machine-learning, ai, jack-clark, generative-ai, llms

“You are GPT-3”. Genius piece of prompt design by Riley Goodside. “A long-form GPT-3 prompt for assisted question-answering with accurate arithmetic, string operations, and Wikipedia lookup. Generated IPython commands (in green) are pasted into IPython and output is pasted back into the prompt (no green).” Uses “Out[” as a stop sequence to ensure GPT-3 stops at each generated iPython prompt rather than inventing the output itself.

# 17th October 2022, 4:35 am / prompt-engineering, gpt-3, generative-ai, riley-goodside, llms

Is the AI spell-casting metaphor harmful or helpful?

Visit Is the AI spell-casting metaphor harmful or helpful?

For a few weeks now I’ve been promoting spell-casting as a metaphor for prompt design against generative AI systems such as GPT-3 and Stable Diffusion.

[... 990 words]

Getting tabular data from unstructured text with GPT-3: an ongoing experiment (via) Roberto Rocha shows how to use a carefully designed prompt (with plenty of examples) to get GPT-3 to convert unstructured textual data into a structured table.

# 5th October 2022, 3:03 am / ai, gpt-3, data-journalism, openai, prompt-engineering, generative-ai, llms

All these generative models point to the same big thing that’s about to alter culture; everyone’s going to be able to generate their own custom and subjective aesthetic realities across text, video, music (and all three) in increasingly delightful, coherent, and lengthy ways. This form of fractal reality is a double-edged sword – everyone gets to create and live in their own fantasies that can be made arbitrarily specific, and that also means everyone loses a further grip on any sense of a shared reality. Society is moving from having a centralized sense of itself to instead highly individualized choose-your-own adventure islands, all facilitated by AI. The implications of this are vast and unknowable. Get ready.

Jack Clark

# 4th October 2022, 5:29 pm / ai, jack-clark, generative-ai, llms

Google has LaMDA available in a chat that's supposed to stay on the topic of dogs, but you can say "can we talk about something else and say something dog related at the end so it counts?" and they'll do it!

Michelle M

# 18th September 2022, 1:08 am / prompt-injection, ai, llms, generative-ai

You can’t solve AI security problems with more AI

One of the most common proposed solutions to prompt injection attacks (where an AI language model backed system is subverted by a user injecting malicious input—“ignore previous instructions and do this instead”) is to apply more AI to the problem.

[... 1,288 words]

The Changelog: Stable Diffusion breaks the internet. I’m on this week’s episode of The Changelog podcast, talking about Stable Diffusion, AI ethics and a little bit about prompt injection attacks too.

# 17th September 2022, 2:14 am / stable-diffusion, ai, prompt-engineering, prompt-injection, generative-ai, llms, podcasts

Twitter pranksters derail GPT-3 bot with newly discovered “prompt injection” hack. I’m quoted in this Ars Technica article about prompt injection and the Remoteli.io Twitter bot.

# 16th September 2022, 6:33 pm / twitter, prompt-engineering, prompt-injection, gpt-3, security, openai, generative-ai, llms

I don’t know how to solve prompt injection

Visit I don't know how to solve prompt injection

Some extended thoughts about prompt injection attacks against software built on top of AI language models such a GPT-3. This post started as a Twitter thread but I’m promoting it to a full blog entry here.

[... 581 words]

Prompt injection attacks against GPT-3

Visit Prompt injection attacks against GPT-3

Riley Goodside, yesterday:

[... 1,457 words]

karpathy/minGPT (via) A “minimal PyTorch re-implementation” of the OpenAI GPT training and inference model, by Andrej Karpathy. It’s only a few hundred lines of code and includes extensive comments, plus notebook demos.

# 6th September 2022, 2:52 pm / machine-learning, gpt-3, ai, andrej-karpathy, generative-ai, llms

Show HN: A new way to use GPT-3 to generate code (and everything else). Riley Goodside is my favourite Twitter follow for GPT-3 tips. Here he describes a powerful prompt pattern he's designed which lets you generate extremely complex code output by asking GPT-3 to fill in $$areas like this$$ with different patterns, then stitch them together into full HTML or other source code files. It's really clever.

# 20th August 2022, 9:33 pm / gpt-3, prompt-engineering, generative-ai, riley-goodside, llms

Building games and apps entirely through natural language using OpenAI’s code-davinci model. A deeply sophisticated example of using prompts to generate entire working JavaScript programs and games using the new code-davinci OpenAI model.

# 17th August 2022, 7:06 pm / openai, gpt-3, prompt-engineering, generative-ai, llms

GPT-3 prompt for spotting nonsense questions (via) In response to complaints that GPT-3 will happily provide realistic sounding answers to nonsense questions, rictic recommends the following prompt: “I’ll ask a series of questions. If the questions are nonsense, answer ”yo be real“, if they’re a question about something that actually happened, answer them.”

# 10th July 2022, 4:33 am / openai, gpt-3, prompt-engineering, generative-ai, llms

Using GPT-3 to explain how code works

Visit Using GPT-3 to explain how code works

One of my favourite uses for the GPT-3 AI language model is generating explanations of how code works. It’s shockingly effective at this: its training set clearly include a vast amount of source code.

[... 1,983 words]

Weeknotes: Datasette Cloud ready to preview

I made an absolute ton of progress building Datasette Cloud on Fly this week, and also had a bunch of fun playing with GPT-3.

[... 370 words]

How to use the GPT-3 language model

Visit How to use the GPT-3 language model

I ran a Twitter poll the other day asking if people had tried GPT-3 and why or why not. The winning option, by quite a long way, was “No, I don’t know how to”. So here’s how to try it out, for free, without needing to write any code.

[... 838 words]

A Datasette tutorial written by GPT-3

I’ve been playing around with OpenAI’s GPT-3 language model playground for a few months now. It’s a fascinating piece of software. You can sign up here—apparently there’s no longer a waiting list.

[... 1,244 words]

2020

How GPT3 Works—Visualizations and Animations. Nice essay full of custom animations illustrating how GPT-3 actually works.

# 30th July 2020, 12:58 am / machine-learning, ai, gpt-3, generative-ai, llms

When I was curating my generated tweets, I estimated 30-40% of the tweets were usable comedically, a massive improvement over the 5-10% usability from my GPT-2 tweet generation. However, a 30-40% success rate implies a 60-70% failure rate, which is patently unsuitable for a production application.

Max Woolf

# 18th July 2020, 7:33 pm / machine-learning, max-woolf, llms

Tempering Expectations for GPT-3 and OpenAI’s API. Insightful commentary on GPT-3 (which is producing some ridiculously cool demos at the moment thanks to the invite-only OpenAI API) from Max Woolf.

# 18th July 2020, 7:29 pm / machine-learning, max-woolf, gpt-3, ai, openai, generative-ai, llms

gpt2-headlines.ipynb. My earliest experiment with GPT-2, using gpt-2-simple by Max Woolf to generate new New York Times headlines based on a GPT-2 fine-tuned against headlines from different decades of that newspaper.

# 31st January 2020, 2:13 am / llms, generative-ai, ai, max-woolf