Simon Willison’s Weblog

LLaVA: Large Language and Vision Assistant (via) Yet another multi-modal model combining a vision model (pre-trained CLIP ViT-L/14) and a LLaMA derivative model (Vicuna). The results I get from their demo are even more impressive than MiniGPT-4. Also includes a new training dataset, LLaVA-Instruct-150K, derived from GPT-4 and subject to the same warnings about the OpenAI terms of service.

# 1:14 am / generative-ai, llama, computer-vision, ai, llms, vicuna

Inside the secret list of websites that make AI chatbots sound smart. Washington Post story digging into the C4 dataset—Colossal Clean Crawled Corpus, a filtered version of Common Crawl that’s often used for training large language models. They include a neat interactive tool for searching a domain to see if it’s included—TIL that simonwillison.net is the 106,649th ranked site in C4 by number of tokens, 189,767 total—0.0001% of the total token volume in C4.

# 1:35 pm / washington-post, llms, ai, generative-ai, training-data

Stability AI Launches the First of its StableLM Suite of Language Models (via) 3B and 7B base models, with 15B and 30B are on the way. CC BY-SA-4.0. “StableLM is trained on a new experimental dataset built on The Pile, but three times larger with 1.5 trillion tokens of content. We will release details on the dataset in due course.”

# 3:47 pm / stable-diffusion, generative-ai, ai, edge-llms, llms

Bard now helps you code (via) Google have enabled Bard’s code generation abilities—these were previously only available through jailbreaking. It’s pretty good—I got it to write me code to download a CSV file and insert it into a SQLite database—though when I challenged it to protect against SQL injection it hallucinated a non-existent “cursor.prepare()” method. Generated code can be exported to a Colab notebook with a click.

# 3:32 pm / google, generative-ai, bard, ai, llms

Introducing PyPI Organizations. Launched at PyCon US today: Organizations allow packages on the Python Package Index to be owned by a group, not an individual user account. “We’re making organizations available to community projects for free, forever, and to corporate projects for a small fee.”—this is the first revenue generating PyPI feature.

# 8:29 pm / open-source, packaging, python, psf, pypi

Rye. Armin Ronacher's take on a Python packaging tool. There are a lot of interesting ideas in this one - it's written in Rust, configured using pyproject.toml and has some very strong opinions, including completely hiding pip from view and insisting you use rye add package instead. Notably, it doesn't use the system Python at all: instead, it downloads a pre-compiled standalone Python from Gregory Szorc's python-build-standalone project - the same approach I used for the Datasette Desktop Electron app.

Armin warns that this is just an exploration, with no guarantees of future maintenance - and even has an issue open titled Should Rye exist?

# 4:02 am / armin-ronacher, packaging, pypi, python, rust, rye

How prompt injection attacks hijack today’s top-end AI – and it’s really tough to fix. Thomas Claburn interviewed me about prompt injection for the Register. Lots of direct quotes from our phone call in here—we went pretty deep into why it’s such a difficult problem to address.

# 6:04 pm / interviews, prompt-engineering, prompt-injection, security, llms, ai, generative-ai

urllib3 v2.0.0 is now generally available. urllib3 is 12 years old now, and is a common low-level dependency for packages like requests and httpx. The biggest new feature in v2 is a higher-level API: resp = urllib3.request(“GET”, “https://example.com”)—a very welcome addition to the library.

# 10 pm / http, python

GPT-3 token encoder and decoder. I built an Observable notebook with an interface to encode, decode and search through GPT-3 tokens, building on top of a notebook by EJ Fox and Ian Johnson.

# 11:48 pm / projects, gpt-3, openai, observable, ai, llms

Trainbot (via) “Trainbot watches a piece of train track, detects passing trains, and stitches together images of them”—check out the site itself too, which shows beautifully stitched panoramas of trains that have recently passed near Jo M’s apartment. Found via the best Hacker News thread I’ve seen in years, “Ask HN: Most interesting tech you built for just yourself?”.

# 2:24 pm / computer-vision, raspberrypi, hacks, go

IF by DeepFloyd Lab (via) New image generation AI model, financially backed by StabilityAI but based on the Google Imagen paper. Claims to be much better at following complex prompts, including being able to generate text! I tried the Colab notebook with “a photograph of raccoon in the woods holding a sign that says ’I will eat your trash’” and it didn’t quite get the text right, see via link for the result.

# 7:34 pm / stable-diffusion, ai, generative-ai

MLC LLM (via) From MLC, the team that gave us Web LLM and Web Stable Diffusion. “MLC LLM is a universal solution that allows any language model to be deployed natively on a diverse set of hardware backends and native applications”. I installed their iPhone demo from TestFlight this morning and it does indeed provide an offline LLM that runs on my phone. It’s reasonably capable—the underlying model for the app is vicuna-v1-7b, a LLaMA derivative.

# 5:43 pm / iphone, generative-ai, llama, ai, edge-llms, llms, mlc

MRSK. A new open source web application deployment tool from 37signals, developed to help migrate their Hey webmail app out of the cloud and onto their own managed hardware. The key feature is one that I care about deeply: it enables zero-downtime deploys by running all traffic through a Traefik reverse proxy in a way that allows requests to be paused while a new deployment is going out—so end users get a few seconds delay on their HTTP requests before being served by the replaced application.

# 11:54 pm / deployment, traefik, ops, 37-signals, zero-downtime