Simon Willison’s Weblog

Prompt Lookup Decoding (via) Really neat LLM optimization trick by Apoorv Saxena, who observed that it’s common for sequences of tokens in LLM input to be reflected by the output—snippets included in a summarization, for example.

Apoorv’s code performs a simple search for such prefixes and uses them to populate a set of suggested candidate IDs during LLM token generation.

The result appears to provide around a 2.4x speed-up in generating outputs! # 23rd January 2024, 2:14 am

AWS Fixes Data Exfiltration Attack Angle in Amazon Q for Business. An indirect prompt injection (where the AWS Q bot consumes malicious instructions) could result in Q outputting a markdown link to a malicious site that exfiltrated the previous chat history in a query string.

Amazon fixed it by preventing links from being output at all—apparently Microsoft 365 Chat uses the same mitigation. # 19th January 2024, 12:02 pm

Open Source LLMs with Simon Willison. I was invited to the Oxide and Friends weekly audio show (previously on Twitter Spaces, now using broadcast using Discord) to talk about open source LLMs, and to respond to a very poorly considered op-ed calling for them to be regulated as “uniquely dangerous”. It was a really fun conversation, now available to listen to as a podcast or YouTube audio-only video. # 17th January 2024, 8:53 pm

On being listed in the court document as one of the artists whose work was used to train Midjourney, alongside 4,000 of my closest friends (via) Poignant webcomic from Cat and Girl.

“I want to make my little thing and put it out in the world and hope that sometimes it means something to somebody else.

Without exploiting anyone.

And without being exploited.” # 16th January 2024, 7:02 pm

Daniel Situnayake explains TinyML in a Hacker News comment. Daniel worked on TensorFlow Lite at Google and co-wrote the TinyML O’Reilly book. He just posted a multi-paragraph comment on Hacker News explaining the term and describing some of the recent innovations in that space.

“TinyML means running machine learning on low power embedded devices, like microcontrollers, with constrained compute and memory.” # 16th January 2024, 6:46 pm

More than an OpenAI Wrapper: Perplexity Pivots to Open Source. I’m increasingly impressed with Perplexity.ai—I’m using it on a daily basis now. It’s by far the best implementation I’ve seen of LLM-assisted search—beating Microsoft Bing and Google Bard at their own game.

A year ago it was implemented as a GPT 3.5 powered wrapper around Microsoft Bing. To my surprise they’ve now evolved way beyond that: Perplexity has their own search index now and is running their own crawlers, and they’re using variants of Mistral 7B and Llama 70B as their models rather than continuing to depend on OpenAI. # 13th January 2024, 6:12 am

Budgeting with ChatGPT (via) Jon Callahan describes an ingenious system he set up to categorize his credit card transactions using GPT 3.5. He has his bank email him details of any transaction over $0, then has an email filter to forward those to Postmark, which sends them via a JSON webhook to a custom Deno Deploy app which cleans the transaction up with a GPT 3.5 prompt (including guessing the merchant) and submits the results to a base in Airtable. # 11th January 2024, 4:40 am

AI versus old-school creativity: a 50-student, semester-long showdown (via) An interesting study in which 50 university students “wrote, coded, designed, modeled, and recorded creations with and without AI, then judged the results”.

This study seems to explore the approach of incremental prompting to produce an AI-driven final results. I use GPT-4 on a daily basis but my usage patterns are quite different: I very rarely let it actually write anything for me, instead using it as brainstorming partner, or to provide feedback, or as API reference or a thesaurus. # 10th January 2024, 11:49 pm

You Can Build an App in 60 Minutes with ChatGPT, with Geoffrey Litt (via) YouTube interview between Dan Shipper and Geoffrey Litt. They talk about how ChatGPT can build working React applications and how this means you can build extremely niche applications that you woudn’t have considered working on before—then to demonstrate that idea, they collaborate to build a note-taking app to be used just during that specific episode recording, pasting React code from ChatGPT into Replit.

Geoffrey: “I started wondering what if we had a world where everybody could craft software tools that match the workflows they want to have, unique to themselves and not just using these pre-made tools. That’s what malleable software means to me.” # 10th January 2024, 11:41 pm

The Random Transformer (via) “Understand how transformers work by demystifying all the math behind them”—Omar Sanseviero from Hugging Face meticulously implements the transformer architecture behind LLMs from scratch using Python and numpy. There’s a lot to take in here but it’s all very clearly explained. # 10th January 2024, 5:09 am

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia. This paper describes a really interesting LLM system that runs Retrieval Augmented Generation against Wikipedia to help answer questions, but includes a second step where facts in the answer are fact-checked against Wikipedia again before returning an answer to the user. They claim “97.3% factual accuracy of its claims in simulated conversation” on a GPT-4 backed version, and also see good results when backed by LLaMA 7B.

The implementation is mainly through prompt engineering, and detailed examples of the prompts they used are included at the end of the paper. # 9th January 2024, 9:30 pm

Mixtral of Experts. The Mixtral paper is out, exactly a month after the release of the Mixtral 8x7B model itself. Thanks to the paper I now have a reasonable understanding of how a mixture of experts model works: each layer has 8 available blocks, but a router model selects two out of those eight for each token passing through that layer and combines their output. “As a result, each token has access to 47B parameters, but only uses 13B active parameters during inference.”

The Mixtral token context size is an impressive 32k, and it compares extremely well against the much larger Llama 70B across a whole array of benchmarks.

Unsurprising but disappointing: there’s nothing in the paper at all about what it was trained on. # 9th January 2024, 4:03 am

OpenAI and journalism. Bit of a misleading title here: this is OpenAI’s first public response to the lawsuit filed by the New York Times concerning their use of unlicensed NYT content to train their models. # 8th January 2024, 6:33 pm

Does GPT-2 Know Your Phone Number? (via) This report from Berkeley Artificial Intelligence Research in December 2020 showed GPT-3 outputting a full page of chapter 3 of Harry Potter and the Philosopher’s Stone—similar to how the recent suit from the New York Times against OpenAI and Microsoft demonstrates memorized news articles from that publication as outputs from GPT-4. # 8th January 2024, 5:26 am

Text Embeddings Reveal (Almost) As Much As Text. Embeddings of text—where a text string is converted into a fixed-number length array of floating point numbers—are demonstrably reversible: “a multi-step method that iteratively corrects and re-embeds text is able to recover 92% of 32-token text inputs exactly”.

This means that if you’re using a vector database for embeddings of private data you need to treat those embedding vectors with the same level of protection as the original text. # 8th January 2024, 5:22 am

GPT in 500 lines of SQL (via) Utterly brilliant piece of PostgreSQL hackery by Alex Bolenok, who implements a full GPT-2 style language model in SQL on top of pg_vector. The final inference query is 498 lines long! # 6th January 2024, 10:55 pm

Microsoft Research relicense Phi-2 as MIT (via) Phi-2 was already an interesting model—really strong results for its size—made available under a non-commercial research license. It just got significantly more interesting: Microsoft relicensed it as MIT open source. # 6th January 2024, 6:06 am

Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations (via) NIST—the National Institute of Standards and Technology, a US government agency, released a 106 page report on attacks against modern machine learning models, mostly covering LLMs.

Prompt injection gets two whole sections, one on direct prompt injection (which incorporates jailbreaking as well, which they misclassify as a subset of prompt injection) and one on indirect prompt injection.

They talk a little bit about mitigations, but for both classes of attack conclude: “Unfortunately, there is no comprehensive or foolproof solution for protecting models against adversarial prompting, and future work will need to be dedicated to investigating suggested defenses for their efficacy.” # 6th January 2024, 4:08 am

My blog’s year archive pages now have tag clouds (via) Inspired by the tag cloud I used in my recent 2023 AI roundup post, I decided to add a tag cloud to the top of every one of my archive-by-year pages showing what topics I had spent the most time with that year.

I already had old code for this, so I pasted it into GPT-4 along with an example of the output of my JSON endpoint from Django SQL Dashboard and had it do most of the work for me. # 4th January 2024, 9:02 pm