Search: “simon-willison”

Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query. — OpenAI Codex base_instruct

Some notes on talkie, a new 'vintage language model' from a team including Alec Radford (yes, that Alec Radford) 'trained on 260B tokens of historical pre-1931 English text' https://simonwillison.net/

Talkie is a project created by the developers @status_effects, @DavidDuvenaud, and @AlecRad. Based on the creator names and context, this likely refers to a conversational AI tool or application, thou

What's new in pip 26.1 - lockfiles and dependency cooldowns! Richard Si describes an excellent set of upgrades to Python's default pip tool for installing dependencies. This version drops support for

This post references a quote from Matt Levine, a financial columnist known for his sharp commentary on finance and markets, shared by Simon Willison on X (formerly Twitter). Without access to the spec

Here's a uv one-liner that downloads and runs the MLX model against a local mp3 file uv run --with mlx-audio python -m mlx_audio.stt.generate --model mlx-community/VibeVoice-ASR-4bit --audio lenny.mp3

@idarbek Having your backups on the same vendor as your production database puts you at risk of your vendor banning your account for some reason (like billing messups, or detected CSAM in user-uploade

Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB

microsoft/VibeVoice VibeVoice is Microsoft's Whisper-style audio model for speech-to-text, MIT licensed and with speaker diarization built into the model. Microsoft released it on January 21st, 2026 b

This post by Simon Willison references a 'perky little fella' related to MiMo-V2.5, likely describing a small or compact AI model or component from the MiMo framework/project version 2.5. Without acce

Speech translation in Google Meet is now rolling out to mobile devices I just encountered this feature via a 'try this out now' prompt in a Google Meet meeting. It kind-of worked! This is Google's imp

The conclusions here feel wrong to me. The two lessons I see are: 1. Don't run agents anywhere they might be able to access production environment credentials - it's on you to know which credentials t

Today OpenAI announced that 'Revenue share payments from OpenAI to Microsoft continue through 2030, independent of OpenAI’s technology progress' That 'independent of OpenAI’s technology progress' frag

For many years, Microsoft and OpenAI's relationship has included a weird clause saying that, should AGI be achieved, Microsoft's commercial IP rights to OpenAI's technology would be null and void. Tha

Simon Willison inquires about running DeepSeek-V4-Flash on Mac hardware, specifically asking about feasibility across different RAM configurations from 512GB down to smaller amounts. This reflects dis

GPT-5.5 prompting guide Now that GPT-5.5 is available in the API, OpenAI have released a wealth of useful tips on how best to prompt the new model. Here's a neat trick they recommend for applications

Simon Willison posted a blog entry reflecting on a notable or surprising development in technology or software, capturing a moment he considered worth documenting for his audience. The post's title 'w

Since GPT-5.4, we’ve unified Codex and the main model into a single system, so there’s no separate coding line anymore. GPT-5.5 takes this further, with strong gains in agentic coding, computer use, a

@scottjla on Twitter in reply to my pelican riding a bicycle benchmark: I feel like we need to stack these tests now I checked to confirm that the model (ChatGPT Images 2.0) added the 'WHY ARE YOU LIK

An update on recent Claude Code quality reports It turns out the high volume of complaints that Claude Code was providing worse quality results over the past two months was grounded in real problems.

... and there's me thinking that sending it out at 9pm Pacific Time on a Thursday evening was safe, surely there wouldn't be any news this evening that I might want to include in there... https://x.co

Chinese AI lab DeepSeek's last model release was V3.2 (and V3.2 Speciale) last December. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, DeepSeek-V

Simon Willison requested that Hugging Face add a repository size sorting option to help users find and filter models by storage requirements, specifically mentioning interest in locating DeepSeek quan

This post references a Hugging Face Models page filtered to show quantized versions of the DeepSeek-V4-Flash model, a lightweight variant of DeepSeek's V4 language model. The page displays community-q

Important: it has been confirmed that ChatGPT Images 2.0 added the 'Why are you like this' sign of its own accord https://x.com/scottjla/status/2047545918665449844 @i_am_brennan @simonw Yes, it did! 🤣

This week's edition of my email newsletter (aka content from this blog delivered to your inbox) features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding i

Release: llm 0.31 New GPT-5.5 OpenAI model: llm -m gpt-5.5. #1418 New option to set the text verbosity level for GPT-5+ OpenAI models: -o verbosity low. Values are low, medium, high. New option for se

More of my notes on DeepSeek V4 - the really big news is the pricing: both DeepSeek-V4-Flash and DeepSeek-V4-Pro are the cheapest models in their categories while benchmarking close to the frontier mo

russellromney/honker 'Postgres NOTIFY/LISTEN semantics' for SQLite, implemented as a Rust SQLite extension and various language bindings to help make use of it. The design of this looks very solid. It

Serving the For You feed One of Bluesky's most interesting features is that anyone can run their own custom 'feed' implementation and make it available to other users - effectively enabling custom alg

The people do not yearn for automation This written and video essay by Nilay Patel explores why AI is unpopular with the general public even as usage numbers for ChatGPT continue to skyrocket. It’s a

These pelicans are kind of angry looking! Left is deepseek-v4-flash, right is deepseek-v4-pro - both generated using OpenRouter via my LLM tool 🚀 DeepSeek-V4 Preview is officially live & open-sourced!

This week's edition of my email newsletter features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new c

GPT-5.5 is out. It's available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I've had some preview access and found it to be a fast, effective and highly capable model. As is usually

LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, us

GPT-5.5 may not be in the official OpenAI API... but it's available via the apparently approved-of Codex API backdoor So I used that to make these pelicans (default and xhigh)! https://simonwillison.n

I've been previewing this in Codex for a few weeks - it's very good! Had some great results from it having it run security reviews against code written using other models Introducing GPT-5.5 A new cla

LiteParse is really neat! It does a great job of extracting text from annoying layouts in PDFs (multiple columns for example) It's only available as a Node.js CLI app, so I vibe-coded up this version

[...] if you ever needed another reason to learn in public by digital gardening or podcasting or streaming or whathaveyou, add on that people will assume you’re more competent than you are. This will

That browser version of LiteParse is available here: https://simonw.github.io/liteparse/ Detailed notes on how I built it using Claude Code (running for an hour) on my blog: https://simonwillison.net/

This is a lot of fun to try out - https://flipbook.page Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.

Within two years you'll be able to prompt inject an entire country Under the directives of the President of the UAE, we launch a new government model. Within two years, 50% of government sectors, serv

Anthropic have now reverted the change to their pricing page, but I've not yet seen any official announcement about what their policies are going to be going forward. More on my blog: https://simonwil

Anthropic really did just hand this one to OpenAI on a plate I don't know what they are doing over there, but Codex will continue to be available both in the FREE and PLUS ($20) plans. We have the com

Anyone else able to duplicate the 34/month pricing for Claude Pro shown in this screenshot? https://x.com/sean_e_callahan/status/2046992927759413647 @simonw Anthropic pricing games? Claude site has Pr

Apparently my blog is mostly about token pricing now, here are some notes on the big changes GitHub Copilot just announced, including pausing new signups entirely https://simonwillison.net/2026/Apr/22