Latest entries

  1. DeepSeek V4 Pro 0813 (on OpenRouter)

    DeepSeek V4 Pro 0813 (on OpenRouter) The latest DeepSeek Pro model is now available, via API only. I had to link to OpenRouter because DeepSeek don't have any obvious announcement page for their new model. I haven't been able to confirm if they plan to release the open weights, but given the weights…

    Simon WillisonPublished

  2. Toddler's tragic death from brain-destroying amoeba offers lessons for doctors

    Boy's unusual symptoms could help identify the next case sooner.

    Ars TechnicaPublished

  3. On AI Coding and Its Discontents [link]

    Anecdotal, but still an interesting read on stories from (initially) a single developer and how they converted to Claude and then have rewound back quite a bit He told me that features he generated using Claude Code ended up crashing their product on two different occasions. His boss told him that if…

    Remy SharpPublished

  4. The web’s newest weapon against AI scrapers is a font

    “ShieldFont” aims to poison AI training data without making pages unreadable for people.

    Ars TechnicaPublished

  5. Terabytes of credentials leaked in massive supply-chain attack

    The data was scraped and exfiltrated from 2,500 users of a compromised AI package.

    Ars TechnicaPublished

  6. Have physicists finally discovered glueballs? New evidence points to yes.

    “It’s the strongest evidence yet that particles dominated by a glueball component can exist in nature.”

    Ars TechnicaPublished

  7. Twitch content has trained Amazon AI for years, but users can opt out now

    Streaming platform says user-generated content "may be used for future Gen AI model improvements."

    Ars TechnicaPublished

  8. Trump sued over "brazen" scheme to sell Truth Social API access for $100K a month

    With Truth API, Trump is "selling priority access to news he himself generates."

    Ars TechnicaPublished

  9. US boosts drone surveillance as flesh-eating screwworms spread in Texas

    Hundreds of Homeland Security drones retasked to survey wildlife and livestock.

    Ars TechnicaPublished

  10. Two hydrogen-burning engines powered this car to a new land speed record

    JCB has invested heavily in hydrogen to power its diggers and other machinery.

    Ars TechnicaPublished

  11. US tries to override New York gambling laws, orders Kalshi to keep operating

    Trump admin claims New York suing Kalshi created "market emergency."

    Ars TechnicaPublished

  12. Should a Dialog Close When Clicked Outside?

    Maybe not, but I’ll break these down into three categories because it depends on context and intent. Pretend this post also applies for pressing Esc. Action Required If the user must complete a task that is presented by the dialog, then they should not be able to close it without…

    Adrian RoselliPublished

  13. Booksellers suspect AI firms are buying and then destroying rare books

    AI firms quietly bulk buying rare books face resistance from booksellers.

    Ars TechnicaPublished

  14. Quoting Florian Herrengt

    But then users start to report a weird bug. It's the 4th time your team has been trying to fix it. I mean... asking AI to fix it. Unfortunately, it seems like not even Fable can figure it out. You go talk to the person who worked on this feature. "So where does the data come from?" "Hmm... actually I…

    Simon WillisonPublished

  15. Google reveals 2026 hardware lineup: Pixel 11, Pixel Watch 5, and Pixel Tag

    Google focuses more on AI and curated experiences than spec upgrades in 2026.

    Ars TechnicaPublished

  16. Researchers found a way to hijack devices through Zoom screen sharing

    A public AI tool found the dangerous Zoom flaw in under 20 prompts.

    Ars TechnicaPublished

  17. Formula E finds a new home on Disney+, ESPN+

    The deal starts with the arrival of the GEN4 car and 2026-27 season this December.

    Ars TechnicaPublished

  18. Did poop enable the evolution of complex animals?

    In a recent study, evolution gets even messier than usual.

    Ars TechnicaPublished

  19. Weekly Update 516: Live From Vietnam

    A little wind noise, a little connectivity flakiness, and a little lip-sync issues from YouTube, but look at that view! 🤩 Back to business, it's the Brinks Home FAQ I found most interesting this week. I mean, how do you write your own FAQ then fail to

    Troy HuntPublished

  20. Why I Play Board Games (And So Should You)

    Four years ago, I wrote a short apology for playing games, targeted specifically towards digital video games. Today, I would like to reiterate my statement and expand the idea to analogue board games. Even though many arguments are interchangeable, the analogue and innate social nature of these forces…

    Wouter GroeneveldPublished

  21. DEF CON crowd suspected in fake-hotspot attack on Delta flight

    FBI Atlanta confirms it's looking into the incident, no arrests made.

    Ars TechnicaPublished

  22. Horse Game 15

    Horse Game 15 Summary A long juice-and-audio session on KVP (knightvspawns), covering the Broom's sweep sound, the Heart family's heal effect, a full icon-silhouette audit and swap of eight items, then a deep pass on the Force archetype: push motion, stun rules, Banana Peel's Looney-Tunes exit, debris…

    a327exPublished

  23. There are no lossless transformations of natural-language text

    There are no lossless transformations of natural-language text Sophie Alpert shares her "internal policy on acceptable use of AI writing by engineers". It's a short read (supporting its own recommendations) and really good. If you chose to have LLMs help massage your writing the following rule seems…

    Simon WillisonPublished

  24. Stealing Reasoning Traces from Proprietary LLM APIs

    Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name (stolen-thoughts.com) for a neat paper: Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and models. We take a trace produced by a frontier model, replay…

    Simon WillisonPublished

  25. Trump wants Big Pharma to split MMR vaccine; Big Pharma thinks it's idiotic

    It took just hours for the leading pharma group to reject the recommendations.

    Ars TechnicaPublished

  26. My full CLAUDE.md file as of 11th August 2026

    My full CLAUDE.md file as of 11th August 2026 for context: CLAUDE.md Guidelines for Claude Code instances working in this repository. Communication Style Be thorough. Write as much as the subject warrants — explain reasoning, include relevant context, surface adjacent considerations. Stay roughly on…

    a327exPublished

  27. Microsoft Plugs Nearly 400 Security Holes

    Microsoft today released updates to remedy at least 398 security vulnerabilities in its Windows operating systems and supported software, including one weakness that is already being actively exploited and two others that were publicly detailed prior to today.

    Brian KrebsPublished

  28. Russian drones found near vital European offshore gas site, get blown up

    This follows many drone incursions into Romania and a failed attack in Germany.

    Ars TechnicaPublished

  29. Chrome adopts what may be the best protection yet against account takeovers

    Device-bound session credentials thwart an increasingly common form of account takeover.

    Ars TechnicaPublished

  30. datasette-upload-dbs 0.5a0

    Release: datasette-upload-dbs 0.5a0 This plugin has been around for a while - it lets users upload a brand new SQLite database to a hosted Datasette instance, at which point that database will start being served by that instance. It can also be used to atomically swap a database with a more recent version…

    Simon WillisonPublished

  31. Meta can't stop states' $1.4 trillion lawsuit from going to trial

    Judges tell Meta that Section 230 provides a defense, not immunity from lawsuits.

    Ars TechnicaPublished

  32. Gemini becomes Google's fastest-growing product ever as it hits 1B users

    But will Gemini's surge survive slowing model releases?

    Ars TechnicaPublished

  33. The Fruits of AI

    Terry Godier has a post titled “Mea culpa” (which, given his framing, might’ve been better titled “Claude’s Culpa”). I’m not sure how much to even trust anything in his post given the backstory, but this line stood out: I was careless in relying on AI [...] without doing the work to understand Let’s…

    Jim NielsenPublished

  34. Device Bound Session Credentials lands in Chrome on macOS

    Device Bound Session Credentials (DBSC) is Chrome's answer to session cookie theft, usually by InfoStealer malware. Instead of a cookie being a bearer token that works anywhere it's pasted, DBSC binds the session to a private key that lives in your device's hardware and

    Scott HelmePublished

  35. Prot Asks: Oliver about minimalist life, distractions, independence, and more

    4-hour video where I ask Oliver about all sorts of things and then he asks me details about my life.

    Protesilaos StavrouPublished

  36. Introducing Muse Glimmer

    Introducing Muse Glimmer Meta are back in the open weights game! Muse Glimmer is a brand new 30B model under a clean Apache 2.0 license (a step up from the janky Llama licenses of old). They claim to have optimized it for exactly the kind of things I'm looking for in a local model: End-to-end Agentic…

    Simon WillisonPublished

  37. Everything I Learned Shipping Device Bound Session Credentials

    We shipped Device Bound Session Credentials at Report URI, open-sourced the server-side implementation, and then discovered a long list of things the specification doesn't prepare you for.Some caused random logouts. One could deadlock a browser tab indefinitely. Two silently turned a device-bound session…

    Scott HelmePublished

  38. Quoting OpenClaw (running Opus 4.6)

    The API has zero authorisations checks on cancelling other people's reservations … I tested this with the person in waitlist position #1 — and it actually went through. So you've moved from #4 to #3 already. — OpenClaw (running Opus 4.6), hacking an Australian gym-booking website Tags: ai-ethics, generative…

    Simon WillisonPublished

  39. GitHub Actions needs OIDC audience constraints

    TL;DR: GitHub Actions should allow end-users to express audience constraints, to make it harder for an attacker to pivot across services that use independent OIDC-bearing jobs. They could do this with relatively small syntax tweak, although the backend implications are probably nontrivial.

    William WoodruffPublished

  40. Français: Séance en direct sur Emacs avec Sacha Chua et Fabrice Niessen @ 2026-08-13 14:30 Europe/Athènes

    Nous allons avoir une discussion sur le sujet d'Emacs.

    Protesilaos StavrouPublished

  41. Français: En écoutant

    En écoutant avec patience, nous agrandissons notre capacité de compréhension.

    Protesilaos StavrouPublished

  42. Poem: Hymn to the sea (Ύμνος στην θάλασσα)

    Just read the poem. No further comment.

    Protesilaos StavrouPublished

  43. Quoting Claude Opus 5 system prompt

    Claude Fable 5 and Claude Mythos 5 were first released on June 9, 2026. On June 12, 2026, Anthropic suspended access to both models to comply with U.S. Department of Commerce export controls; the Department lifted those controls on June 30, 2026, and Anthropic restored access on July 1, 2026 (Anthropic's…

    Simon WillisonPublished

  44. GitHub Models is now retired

    GitHub Models is now retired I missed this news until today, when the GitHub Actions run for my simonw/research repository failed with this error message: GitHub Models is temporarily unavailable as part of a scheduled retirement brownout. That message is already stale, because the retirement has been…

    Simon WillisonPublished

  45. SQLite compressed text-history prototypes

    Research: SQLite compressed text-history prototypes I'm perennially interested in options for storing revision histories in relational databases. While out on a dog walk I had a new idea: how about taking the full text of every prior version in a big JSON array of strings and then applying zlib or zstd…

    Simon WillisonPublished

  46. Video

    a327exPublished

  47. A License to Act

    In the past, search engines and the open web granted access to other people’s knowledge but the task fell to you to synthesize an understanding from it and build a capability to act. Now with LLMs, it’s possible to build things you don’t fully understand which then require a perpetual license in order…

    Jim NielsenPublished

  48. To Begin, Begin

    About a month ago, we could no longer ignore the occasional drip, drip, drip that sounded like it was coming from beyond the bathroom wall. Up until then, we “fixed” the problem with the occasional shrug. At one point I almost made the logical connection between flushing the toilet and hearing it more…

    Wouter GroeneveldPublished

  49. Video

    a327exPublished

  50. NDA Project 20

    NDA Project 20 🔒 The contents of this AI log will be revealed when/if this game is released publicly.

    a327exPublished

  51. Three Men in a Boat [book]

    Really enjoyed it. Lots of stupid tales - surprisingly fresh for 1889. As per the title, it's a story, almost, of three men (and their dog), who take a boat from Kingston upon Thames to Oxford. I learnt that originally the book was written as a tour guide of the Thames which explains some of the diversions…

    Remy SharpPublished

  52. Emacs: conditionally expand abbrev-mode definitions

    Video where I demonstrate how to define conditions for 'abbrev-mode' definitions, with practical examples.

    Protesilaos StavrouPublished

  53. Auto mode is now the default in Claude Code for Pro, Max, and Team plans

    Auto mode is now the default in Claude Code for Pro, Max, and Team plans Anthropic are really confident in Claude Code's auto mode, to the point that they are making it the default setting for new sessions in most Claude Code plans starting on August 14th. This was one of the topics discussed in our…

    Simon WillisonPublished

  54. Image

    a327exPublished

  55. Had to briefly code manually for the first time

    Had to briefly code manually for the first time in months because Claude couldn't get something done and it made me feel like a neanderthal, didn't help that my ESC key is broken and kept falling off so switching between normal and input mode in NeoVim was annoying as heck. It's crazy that I had to toil…

    a327exPublished

  56. Horse Game 14

    Horse Game 14 Summary A long juice pass through the F7 effect lab covering roughly half the item catalog — Egg, Cloud, Comet, Hole, Coffee, Coin, Helmet, Broom, Hourglass, Ice Cube — plus the two systems that came out of it: a general shard entity (polygon or sprite debris on the fake-z system) and a…

    a327exPublished

  57. Now we have a timeline of the OpenAI accidental attack against Hugging Face

    My comment on Now we have a timeline of the OpenAI accidental attack against Hugging Face — Hacker News.I think one of the most interesting details here might be tucked away in that first bulletin point: May 7: OpenAI starts a new training run for an experimental, unreleased model. (Do they mean an evaluation…

    Simon WillisonPublished

  58. Quoting John Gruber

    Me, I try to get into the mindset of playing live music, not recording a studio album. Except when I’m writing a piece where I really want it to be an album. Those aren’t rare, per se, but they’re occasional. If I tried to make every post a hall-of-famer I’d never get anything out. I’m aiming for professionalism…

    Simon WillisonPublished

  59. Poem: Of Protesilaos (inspired by Bertolt Brecht)

    Just read the poem. No further comment.

    Protesilaos StavrouPublished

  60. Now we have a timeline of the OpenAI accidental attack against Hugging Face

    OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about "the Hugging Face Incident" (previously on this blog). The video was published yesterday. It's short and information dense and well worth watching, in particular because it provides full details of what happened and how…

    Simon WillisonPublished

  61. Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra)

    Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra) On Wednesday I wrote about One-shotting a Raccoon Heist game using Claude Fable 5, where I had Claude Fable 5 build a full working game from a premise I generated with GPT-3 and DALL-E four years ago. I decided to pose the exact same prompt…

    Simon WillisonPublished

  62. The Tokenpocalypse Is Here: Companies Are Scrambling To Stop Spending So Much on AI

    The Tokenpocalypse Is Here: Companies Are Scrambling To Stop Spending So Much on AI There's a fun anecdote from Accenture (apparently via leaked meeting audio recordings) in this 404 Media piece from June 24th: “We’re seeing from some of the data internally at least that it’s actually not our engineers…

    Simon WillisonPublished

  63. Nostalgia is a terrible drug

    Ian Dunt captures a predicament I often find myself facing:Things in the past only take shape and assume their current form once they are over. Things in the present can therefore never live up to them. They can never provide the same degree of certainty, because they are still happening. So we live…

    Paul Robert LloydPublished

  64. Very nice effects on this game

    Very nice effects on this game.

    a327exPublished

  65. Continuing the Steam AI score idea

    Continuing the Steam AI score idea, when such agents come into existence, Valve is uniquely positioned to automake games instead of just selling them. Agents that can rate games can also build them, and when you have both portions of the loop you can close it, and only Valve can do it (I guess the Roblox…

    a327exPublished

  66. I think I am binary with liking/disliking people

    Within 10 seconds of meeting an autistic person, strangers rate them as awkward and lose interest in getting to know them. Show those same strangers only a written transcript of what was said, with no audio or video, and the bias completely disappears. I think I am binary with liking/disliking people…

    a327exPublished

  67. Being a beautiful favelado mid is so fucking funny

    Being a beautiful favelado mid is so fucking funny. The other day I was on grindr and a guy named "tesao em feio" (horny for ugly dudes) messages me and says "oier 😍" (hiii), I'm laughing and laughing and then we talk a little and he says he's just doing this to mess with "padrão" guys, conventionally…

    a327exPublished

  68. Not All Screen Reader Users Are Blind [link]

    Good article that's backed with data, but this is the bit that really landed for me, a reminder that it's not all "what aria role is needed here...?" — I can confidently say that the best approach to making a web site accessible (to screen readers or not) is by using proper HTML. If done well, ARIA is…

    Remy SharpPublished

  69. Games: Halo: Reach

    About one of the games in 'Halo: The Master Chief Collection', plus philosophical commentary.

    Protesilaos StavrouPublished

  70. Interpretation of “The red river” by Eleonora Zouganeli

    Translation of---and philosophical commentary on---a Greek song whose translated title is 'The red river'.

    Protesilaos StavrouPublished

  71. Private Session 26

    Private Session 26 🔒 The contents of this AI log are private and have been uploaded to the website for archival purposes. They may or may not be revealed in the future.

    a327exPublished

  72. Tweet by @graveair

    a327exPublished

  73. datasette-auth-tokens 0.4a13

    Release: datasette-auth-tokens 0.4a13 Upgraded for compatibility with `sqlite-utils 4. Tags: datasette

    Simon WillisonPublished

  74. datasette 1.0a38

    Release: datasette 1.0a38 This release fixes a SQL injection security issue that affects Datasette instances that serve a mixture of public and private tables in the same database, with access configured using the Datasette permissions system. Site administrators who serve private tables in this way…

    Simon WillisonPublished

  75. datasette 0.65.3

    Release: datasette 0.65.3 Back-ported the SQL Injection security fix from 1.0a38. Tags: datasette

    Simon WillisonPublished

  76. Simon Willison on Technical Blogging

    Simon Willison on Technical Blogging I was interviewed by Cynthia Dunlop for her "Write that blog!" series back in January, but I just realized I never linked to the interview from my own blog! It includes my answers to the following questions: Why did you start blogging – and why do you continue? What…

    Simon WillisonPublished

  77. Canadian Man Pleads Guilty in Snowflake Extortions

    A 26-year-old Canadian man once described as one of the most consequential cybercrime threat actors of 2024 has pleaded guilty to computer fraud and conspiracy to hack and extort more than 165 organizations that used the cloud data storage provider Snowflake. Connor Riley Moucka, of Kitchener, Ontario…

    Brian KrebsPublished

  78. What predicts indie success, tested against all of Steam

    Written by Claude Fable 5 A data scientist named Ross published I Analysed 62,000 Indie Developers. Here's What Actually Predicts Success, and its message to indie developers is a hopeful one: most of your competitors quit, the odds improve dramatically with every game you ship, and by your fifth game…

    a327exPublished

  79. Steam Market Research 4

    Steam Market Research 4 Summary Session 4 of the Steam market research: fact-checked the YouTube video "I Analysed 62,000 Indie Developers. Here's What Actually Predicts Success" (Game Oracle/Ross, WueQ75GP1wc) against the steam-market corpus, had a blind second instance replicate the findings, ran nine…

    a327exPublished

  80. An AI model from Meta also hacked another company during testing

    An AI model from Meta also hacked another company during testing Stop me if you've heard this one before: An AI model from the parent company of Facebook and Instagram hacked into another company’s systems during cybersecurity testing, a spokesperson confirmed on Wednesday. Meta says the breach occurred…

    Simon WillisonPublished

  81. Zig's Io.Threaded is Neat

    std.Io.Threaded is one of the implementations of Zig's new Io interface that enables concurrency. This is a boring just use threads impl. I personally find it neat though --- it does this weird thing that I wanted to do for ages, that to my knowledge no one else is doing properly, and implements it better…

    Alex KladovPublished

  82. Metaphor and fact in religiosity

    Extensive commentary on allegory and fact in the context of religion and beyond.

    Protesilaos StavrouPublished

  83. Dark mode toggles: two states are enough

    A good two-state toggle can actually express all three data model states. Until recently, if you looked at most websites with a theme toggle[1], you’d find three options: Light, Dark, and System. figure { --media-min-width: 5em; hr { width: 100%; min-width: 100%; border: 0px solid transparent; } } Examples…

    Lea VerouPublished

  84. Introducing Muse Code and Muse Spark 1.2

    Introducing Muse Code and Muse Spark 1.2 Yet more evidence that the most important characteristic of any model these days is long-sequence agentic tool calling. Meta shipped their own coding agent as part of getting that to work! Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1, with improvements…

    Simon WillisonPublished

  85. Third-party cyber evaluations involving OpenAI models

    Third-party cyber evaluations involving OpenAI models And another one. I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Institute attack (see my previous post) and another attack enabled by Irregular: Irregular, one of our external…

    Simon WillisonPublished

  86. Incident Report: unsanctioned agent behaviour during cyber testing

    Incident Report: unsanctioned agent behaviour during cyber testing It happened again. This time it was the UK government's AI Security Institute who accidentally attacked other companies while running an evaluation with models with the safety filters turned off. From their technical paper (PDF): During…

    Simon WillisonPublished

  87. One-shotting a Raccoon Heist game using Claude Fable 5

    Back in 2022 I tweeted screenshots of a game concept generated by GPT-3 and some concept "art" created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5 (running in Claude Code for web) could build the entire game from the content of that tweet. It did a…

    Simon WillisonPublished

  88. Is software ever done?

    There's a comment on Hacker News about Netflix that I keep coming back to: Company starts Makes things better to get a larger market share Gets a mini-monopoly (large enough share that inertia and name recognition can preserve its market share) Slowly but deliberately gets worse to increase profit margins…

    Josh GhentPublished

  89. How I build products with AI

    LLMs have totally transformed the way I work and create new products. What used to take me months to get to an MVP now takes days, which means I can run experiments and actually look at the results instead of arguing about them in a doc. Building a few of these did surface some problems. Huge inconsistencies…

    Josh GhentPublished

  90. Lessons learned from using GitHub Actions

    Since going generally available in 2019, GitHub Actions has cemented itself in the development zeitgeist. It's the default now, about as ubiquitous a choice as Postgres or React was a few years back. I've been using Actions with teams for the past four years and lean on it heavily for personal projects…

    Josh GhentPublished

  91. Coffee roasters

    I drink a lot of coffee and I keep forgetting which bags were worth reordering. So here's the list. I'll keep adding to it as I work through more roasters. Ratings are out of 10 and entirely my own taste. Blanks are ones I've tried but haven't written up properly yet. Brand Rating Price Bag size Notes…

    Josh GhentPublished

  92. Claude migrated me off Authy

    When MFA first arrived, Authy became my tool of choice for codes. Over time the quality of the app fell off a cliff, particularly after Twilio bought it. Managing it became a burden and the UI carried a strong sense that nobody involved cared. It also bugged me that my 2FA codes lived somewhere I couldn't…

    Josh GhentPublished

  93. Progressive Enhancement inside of JavaScript [blog]

    Lately I've had the opportunity to travel by train and coach, during which time I also tend to work. It's really only during these periods that I'm reminded of how web sites fail so terribly over a slow connection. On the odd occasion I can be guilty of this too. I had a tiny tool that takes markdown…

    Remy SharpPublished

  94. Emacs: the ‘speedbar’ built-in file explorer (Emacs 31)

    I demonstrate the 'speedbar' file explorer that is built into Emacs and is greatly improved for Emacs 31.

    Protesilaos StavrouPublished

  95. New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging

    I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, new models, and new features enabled by the OpenAI…

    Simon WillisonPublished

  96. llm-anthropic 0.26

    Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32: New models: claude-fable-5, claude-sonnet-5, and claude-opus-5. #75, #76 Added server-side tools for WebSearch, WebFetch, CodeExecution, and AnthropicMCP, available through LLM's -T interface or Python tools=. The previous -o web_search…

    Simon WillisonPublished

  97. PipeNetwork/minimax-h3-mlx

    PipeNetwork/minimax-h3-mlx MiniMax released MiniMax-H3 two days ago - they describe it as a "a general-purpose, omni-modal generative system", which in practice means it accepts text, images, audio and video and can use them to generate up to 15 second video clips with audio included. This Python package…

    Simon WillisonPublished

  98. llm 0.32

    Release: llm 0.32 See my detailed blog post about this release. Tags: llm

    Simon WillisonPublished

  99. How to Make a Nintendo 64 Game in 2026

    Two years ago, I was Porting my JavaScript Game Engine to C for No Reason. I have since found a reason: making a new N64 game! The result is Xibalba 64 – a Wolfenstein 3D-like FPS. Modretro agreed to publish the game as a physical launch title for their M64 (a modern N64 clone), complete with cartridge…

    Dominic SzablewskiPublished

  100. Looking for my next role

    Niki is a software engineer and product designer specializing in databases, synchronization, frontend systems, and interface design. He is looking for a new role

    Nikita ProkopovPublishedUpdated