Simon Willison’s Weblog

Use an llm to automagically generate meaningful git commit messages. Neat, thoroughly documented recipe by Harper Reed using my LLM CLI tool as part of a scheme for if you’re feeling too lazy to write a commit message—it uses a prepare-commit-msg Git hook which runs any time you commit without a message and pipes your changes to a model along with a custom system prompt.

# 4:06 am / llm, ai, git, generative-ai

3Blue1Brown: Attention in transformers, visually explained. Grant Sanderson publishes animated explainers of mathematical topics on YouTube, to over 6 million subscribers. His latest shows how the attention mechanism in transformers (the algorithm behind most LLMs) works and is by far the clearest explanation I’ve seen of the topic anywhere.

I was intrigued to find out what tool he used to produce the visualizations. It turns out Grant built his own open source Python animation library, manim, to enable his YouTube work.

# 4:12 pm / llms, ai, generative-ai

How we built JSR (via) Really interesting deep dive by Luca Casonato into the engineering behind the new JSR alternative JavaScript package registry launched recently by Deno.

The backend uses PostgreSQL and a Rust API server hosted on Google Cloud Run.

The frontend uses Fresh, Deno’s own server-side JavaScript framework which leans heavily in the concept of “islands”—a progressive enhancement technique where pages are rendered on the server and small islands of interactivity are added once the page has loaded.

# 3:49 pm / rust, deno, progressive-enhancement, javascript, postgresql

Lessons after a half-billion GPT tokens (via) Ken Kantzer presents some hard-won experience from shipping real features on top of OpenAI’s models.

They ended up settling on a very basic abstraction over the chat API—mainly to handle automatic retries on a 500 error. No complex wrappers, not even JSON mode or function calling or system prompts.

Rather than counting tokens they estimate tokens as 3 times the length in characters, which works well enough.

One challenge they highlight for structured data extraction (one of my favourite use-cases for LLMs): “GPT really cannot give back more than 10 items. Trying to have it give you back 15 items? Maybe it does it 15% of the time.”

(Several commenters on Hacker News report success in getting more items back by using numbered keys or sequence IDs in the returned JSON to help the model keep count.)

# 8:54 pm / openai, llms, ai, generative-ai, prompt-engineering

redka (via) Anton Zhiyanov’s new project to build a subset of Redis (including protocol support) using Go and SQLite. Also works as a Go library.

The guts of the SQL implementation are in the internal/sqlx folder.

# 3:21 pm / sqlite, anton-zhiyanov, go, redis

OpenAI Batch API (via) OpenAI are now offering a 50% discount on batch chat completion API calls if you submit them in bulk and allow for up to 24 hours for them to be run.

Requests are sent as a newline-delimited JSON file, with each line looking something like this:

{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is 2+2?"}]}}

You upload a file for the batch, kick off a batch request and then poll for completion.

This makes GPT-3.5 Turbo cheaper than Claude 3 Haiku - provided you're willing to wait a few hours for your responses.

# 5:58 pm / openai, llms, ai, generative-ai

inline-snapshot. I'm a big fan of snapshot testing, where expected values are captured the first time a test suite runs and then asserted against in future runs. It's a very productive way to build a robust test suite.

inline-snapshot by Frank Hoffmann is a particularly neat implementation of the pattern. It defines a snapshot() function which you can use in your tests:

assert 1548 * 18489 == snapshot()

When you run that test using pytest --inline-snapshot=create the snapshot() function will be replaced in your code (using AST manipulation) with itself wrapping the repr() of the expected result:

assert 1548 * 18489 == snapshot(28620972)

If you modify the code and need to update the tests you can run pytest --inline-snapshot=fix to regenerate the recorded snapshot values.

# 4:04 pm / testing, python, pytest

Google NotebookLM Data Exfiltration (via) NotebookLM is a Google Labs product that lets you store information as sources (mainly text files in PDF) and then ask questions against those sources—effectively an interface for building your own custom RAG (Retrieval Augmented Generation) chatbots.

Unsurprisingly for anything that allows LLMs to interact with untrusted documents, it’s susceptible to prompt injection.

Johann Rehberger found some classic prompt injection exfiltration attacks: you can create source documents with instructions that cause the chatbot to load a Markdown image that leaks other private data to an external domain as data passed in the query string.

Johann reported this privately in the December but the problem has not yet been addressed. UPDATE: The NotebookLM team deployed a fix for this on 18th April.

A good rule of thumb is that any time you let LLMs see untrusted tokens there is a risk of an attack like this, so you should be very careful to avoid exfiltration vectors like Markdown images or even outbound links.

# 9:28 pm / prompt-injection, security, google, generative-ai, ai, llms, rag, markdown-exfiltration, johann-rehberger, notebooklm

Scammers are targeting teenage boys on social media—and driving some to suicide. (via) Horrifying in depth report describing sextortion scams: a scammer tricks a teenage boy into sending them reciprocal nude photos, then instantly starts blackmailing them by threatening to forward those photos to their friends and family members. Most online scams take weeks or even months to play out—these scams can turn to blackmail within minutes.

# 3:10 am / scams

mistralai/mistral-common. New from Mistral: mistral-common, an open source Python library providing "a set of tools to help you work with Mistral models".

So far that means a tokenizer! This is similar to OpenAI's tiktoken library in that it lets you run tokenization in your own code, which crucially means you can count the number of tokens that you are about to use - useful for cost estimates but also for cramming the maximum allowed tokens in the context window for things like RAG.

Mistral's library is better than tiktoken though, in that it also includes logic for correctly calculating the tokens needed for conversation construction and tool definition. With OpenAI's APIs you're currently left guessing how many tokens are taken up by these advanced features.

Anthropic haven't published any form of tokenizer at all - it's the feature I'd most like to see from them next.

Here's how to explore the vocabulary of the tokenizer:

MistralTokenizer.from_model(
    "open-mixtral-8x22b"
).instruct_tokenizer.tokenizer.vocab()[:12]

['<unk>', '<s>', '</s>', '[INST]', '[/INST]', '[TOOL_CALLS]', '[AVAILABLE_TOOLS]', '[/AVAILABLE_TOOLS]', '[TOOL_RESULTS]', '[/TOOL_RESULTS]']

# 12:39 am / mistral, anthropic, python, generative-ai, openai, ai, llms, prompt-engineering, rag

llm-reka. My new plugin for running LLM prompts against the Reka family of API hosted LLM models: reka-core ($10 per million input), reka-flash (80c per million) and reka-edge (40c per million).

All three of those models are trained from scratch by a team that includes several Google Brain alumni.

Reka Core is their most powerful model, released on Monday 15th April and claiming benchmark scores competitive with GPT-4 and Claude 3 Opus.

# 3:17 am / llm, generative-ai, projects, ai, llms

How cheap, outsourced labour in Africa is shaping AI English. The word “delve” has been getting a lot of attention recently as an example of something that might be an indicator of ChatGPT generated content.

One example: articles on medical research site PubMed now use “delve” 10 to 100 times more than a few years ago!

Nigerian Twitter took offense recently to Paul Graham’s suggestion that “delve” is a sign of bad writing. It turns out Nigerian formal writing has a subtly different vocabulary.

Alex Hern theorizes that the underlying cause may be related. Companies like OpenAI frequently outsource data annotation to countries like Nigeria that have excellent English skills and low wages. RLHF (reinforcement learning from human feedback) involves annotators comparing and voting on the “best” responses from the models.

Are they teaching models to favour Nigerian-English? It’s a pretty solid theory!

# 4:04 pm / llms, ai, ethics, generative-ai

Andrej Karpathy’s Llama 3 review. The most interesting coverage I’ve seen so far of Meta’s Llama 3 models (8b and 70b so far, 400b promised later).

Andrej notes that Llama 3 trained on 15 trillion tokens—up from 2 trillion for Llama 2—and they used that many even for the smaller 8b model, 75x more than the chinchilla scaling laws would suggest.

The tokenizer has also changed—they now use 128,000 tokens, up from 32,000. This results in a 15% drop in the tokens needed to represent a string of text.

The one disappointment is the context length—just 8,192, 2x that of Llama 2 and 4x LLaMA 1 but still pretty small by today’s standards.

If early indications hold, the 400b model could be the first genuinely GPT-4 class openly licensed model. We’ll have to wait and see.

# 8:50 pm / andrej-karpathy, generative-ai, llama, ai, llms

A POI Database in One Line (via) Overture maps offer an extraordinarily useful freely licensed databases of POI (point of interest) listings, principally derived from partners such as Facebook and including restaurants, shops, museums and other locations from all around the world.

Their new "overturemaps" Python CLI utility makes it easy to quickly pull subsets of their data... but requires you to provide a bounding box to do so.

Drew Breunig came up with this delightful recipe for fetching data using LLM and gpt-3.5-turbo to fill in those bounding boxes:

overturemaps download --bbox=$(llm 'Give me a bounding box for Alameda, California expressed as only four numbers delineated by commas, with no spaces, longitude preceding latitude.') -f geojsonseq --type=place | geojson-to-sqlite alameda.db places - --nl --pk=id

# 2:44 am / drew-breunig, llm, gis, geojson, overture

Ruff v0.4.0: a hand-written recursive descent parser for Python. The latest release of Ruff—a Python linter and formatter, written in Rust—includes a complete rewrite of the core parser. Previously Ruff used a parser borrowed from RustPython, generated using the LALRPOP parser generator. Victor Hugo Gomes contributed a new parser written from scratch, which provided a 2x speedup and also added error recovery, allowing parsing of invalid Python—super-useful for a linter.

I tried Ruff 0.4.0 just now against Datasette—a reasonably large Python project—and it ran in less than 1/10th of a second. This thing is Fast.

# 5 am / rust, python, compilers, ruff, astral

llm-gpt4all. New release of my LLM plugin which builds on Nomic's excellent gpt4all Python library. I've upgraded to their latest version which adds support for Llama 3 8B Instruct, so after a 4.4GB model download this works:

llm -m Meta-Llama-3-8B-Instruct "say hi in Spanish"

# 5:58 pm / nomic, llm, plugins, projects, generative-ai, ai, llms, llama, edge-llms

Tips on Adding JSON Output to Your CLI App (via) Kelly Brazil - also the author of jc, the neat CLI tool that converts the output of common Unix utilities such as dig into JSON - provides some useful do's and don'ts for adding JSON output as an option to a command-line tool.

Kelly recommends defaulting to arrays of flat objects - or newline-delimited objects - and suggests including an "unbuffer" option for streaming tools that discourages the OS from buffering output that is being sent through a pipe.

# 9:43 pm / json, cli

doom-htop (via) Ludicrous, brilliant hack: it runs Doom, converts each frame to ASCII art, then runs one process for each line of ASCII and sets each process to allocate enough memory such that sorting by M_VIRT will show the lines in the correct order. Then it updates the argv[0] for each process on every frame such that htop displays the state of the game.

Probably only works on Ubuntu.

From the FAQ: “Q: Why did you make this? A: I thought it would be funny.”

# 1:59 pm / hacks

tiny-world-map (via) I love this project. It’s a JavaScript file (694K uncompressed, 283KB compressed) which can be used with the Leaflet mapping library and provides a SVG base map of the world with country borders and labels for every world city with a population more than 48,000—10,000 cities total.

This means you can bundle an offline map of the world as part of any application that doesn’t need a higher level of detail. A lot of smaller island nations are missing entirely though, so this may not be right for every project.

It even includes a service worker to help implement offline mapping support, plus several variants of the map with less cities that are even smaller.

# 10:11 pm / svg, serviceworkers, javascript, gis, mapping

qrank (via) Interesting and very niche project by Colin Dellow.

Wikidata has pages for huge numbers of concepts, people, places and things.

One of the many pieces of data they publish is QRank—“ranking Wikidata entities by aggregating page views on Wikipedia, Wikispecies, Wikibooks, Wikiquote, and other Wikimedia projects”. Every item gets a score and these scores can be used to answer questions like “which island nations get the most interest across Wikipedia”—potentially useful for things like deciding which labels to display on a highly compressed map of the world.

QRank is published as a gzipped CSV file.

Colin’s hikeratlas/qrank GitHub repository runs weekly, fetches the latest qrank.csv.gz file and loads it into a SQLite database using SQLite’s “.import” mechanism. Then it publishes the resulting SQLite database as an asset attached to the “latest” GitHub release on that repo—currently a 307MB file.

The database itself has just a single table mapping the Wikidata ID (a primary key integer) to the latest QRank—another integer. You’d need your own set of data with Wikidata IDs to join against this to do anything useful.

I’d never thought of using GitHub Releases for this kind of thing. I think it’s a really interesting pattern.

# 10:28 pm / wikipedia, github-actions, sqlite, colin-dellow