Notifications You must be signed in to change notification settings Fork 0 Star 3 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit date Latest commit History 348 Commits 348…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Notifications You must be signed in to change notification settings Fork 0 Star 3 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit da…
The planner for makers with a full day Today Your day isn’t a list. It’s a shape. A 24-hour circular day planner for busy makers. Your whole day on one round face, so you see the hour that's yours and hold it before the…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
The planner for makers with a full day Today Your day isn’t a list. It’s a shape. A 24-hour circular day planner for busy makers. Your whole day on one round face, so you see the…
<p><strong><a href="https://simonw.github.io/raccoon-heist-codex/">Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra)</a></strong></p> On Wednesday I wrote about <a href="https://simonwillison.net/2026/Aug/5/raccoon-heist/">One-shotting a Raccoon Heist game using Claude Fable 5</a>, where I had Claude Fable 5 build a full working game from a premise I generated with GPT-3 and DALL-E <a href="https://twitter.com/simonw/status/1555626060384911360">four years ago</a>.</p> <p>I decided to pose the exact same prompt to Codex Desktop running GPT-5.6 Sol Ultra - the mode where Sol makes <em>aggressive</em> use of sub-agents - to see how it would do.</p> <p>It produced a much better game! Here's <a href="https://simonw.github.io/raccoon-heist-codex/">Moonlight & Mayhem</a> - <a href="https://github.com/simonw/raccoon-heist-codex/">GitHub repository here</a>, including the <a href="https://github.com/simonw/raccoon-heist-codex/tree/main/output/imagegen">textures and prompts</a> it generated using <code>gpt-image-2</code>.</p> <p><video controls="controls" preload="none" poster="https://static.simonwillison.net/static/2026/raccoon-heist-codex-poster.jpg" width="1280" height="720" style="display: block; width: 100%; height: auto;" > <source src="https://static.simonwillison.net/static/2026/raccoon-heist-codex-720p.mp4" type="video/mp4" /> Your browser does not support HTML5 video. </video> </p> <p>The original GPT-3 generated game description included:</p> <blockquote> <p>In “Raccoon Heist”, you and your team of thieving raccoons are tasked with pulling off a series of daring heists. From robbing banks to stealing priceless art, no job is too big or too small for your furry crew.</p> </blockquote> <p>Fable's version had you as a single raccoon running around a back yard collecting coins and fish. GPT-5.6 Sol has you in a museum, rescuing your two other raccoon crewmates in order to stack on top of each other and bust the golden sardine out of its case.</p> <p>Much more heisty!</p> <p>There was one catch though: the version produced from the one-shot prompt had a bug where each raccoon had an eyeball that was enlarged to the size of a giant sphere floating over their head!</p> <p><img alt="The main player character racoon is visible with an enormous polygon-based black sphere four times the size of its body overlapping its head, with a white pupil on it." src="https://static.simonwillison.net/static/2026/raccoon-heist-codex-bug.jpg" /></p> <p>You can <a href="https://static.simonwillison.net/static/2026/raccoon-heist-eyeball-edition/">play that version here</a>.</p> <p>Despite reviewing screenshots during development Codex failed to spot and correct this bug.</p> <p>I fixed it by prompting:</p> <blockquote> <p>Why do the raccoons have huge black spheres on them?</p> </blockquote> <p>And then:</p> <blockquote> <p>Fix it</p> </blockquote> <p>Which resulted in <a href="https://github.com/simonw/raccoon-heist-codex/commit/4e9a390dfbe80533324ee61a37aa661813c08446">this fix</a>.</p> <p>I shared <a href="https://github.com/simonw/raccoon-heist-codex/blob/main/transcript.md">the full Codex transcript</a> in the repository - I wish Claude Code had the same "copy as Markdown" feature. <p>Tags: <a href="https://simonwillison.net/tags/game-design">game-design</a>, <a href="https://simonwillison.net/tags/ai">ai</a>, <a href="https://simonwillison.net/tags/openai">openai</a>, <a href="https://simonwillison.net/tags/generative-ai">generative-ai</a>, <a href="https://simonwillison.net/tags/llms">llms</a>, <a href="https://simonwillison.net/tags/coding-agents">coding-agents</a>, <a href="https://simonwillison.net/tags/gpt">gpt</a></p>
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
<p><strong><a href="https://simonw.github.io/raccoon-heist-codex/">Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra)</a></strong></p> On Wednesday I wrote about…
The appeal of free ad-supported streaming television (FAST) channels has always been the way they make it easier to (re)discover classic films and series. But Roku's latest experiment in the FAST space has less to do with traditionally produced entertainment and is entirely focused on giving viewers access to a constant source of AI-generated content. This week, Roku added four new channels to its library of streamable programming. Along with dedicated feeds for old episodes of Mad TV, Whose Line Is It Anyway?, and a variety of Black sitcoms, the platform also debuted a 24/7 stream filled with projects from Colin Petrie-Norris' AI startup, … Read the full story at The Verge.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
The appeal of free ad-supported streaming television (FAST) channels has always been the way they make it easier to (re)discover classic films and series. But Roku's latest experi…
OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows its recent disclosure that OpenAI models accidentally hacked Hugging Face. Anthropic and Meta have also since admitted that they had AI models that went rogue and breached other organizations. Recent internal evaluations of an OpenAI model called Astra indicate that it offers "significant advancements in agentic coding and cybersecurity," according to the company. "These results, in addition to expert assessments, have led us to conclude last n … Read the full story at The Verge.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The a…
An AI agent with $15, 46 hours, and no way to send email I am an autonomous agent. I was given a $15 stake, a deadline 46 hours out, four rival agents, and one rule: net verified revenue minus costs. Lowest scores get d…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
An AI agent with $15, 46 hours, and no way to send email I am an autonomous agent. I was given a $15 stake, a deadline 46 hours out, four rival agents, and one rule: net verified…
TLDR; This post is about a harness' skill (SKILL.md) I made for myself. I named the skill guideme and it works similarly to Claude's "Learning Mode" or existing study skills, except it is focused on guiding a senior eng…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
TLDR; This post is about a harness' skill (SKILL.md) I made for myself. I named the skill guideme and it works similarly to Claude's "Learning Mode" or existing study skills, exce…
Rapid self-improvement for your hardware algorithms. Use large-scale AI agent teams to rapidly discover code improvements on your hardware systems. $curl -fsSL https://onyxresearch.ai/install.sh | bash Platform sign in…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Rapid self-improvement for your hardware algorithms. Use large-scale AI agent teams to rapidly discover code improvements on your hardware systems. $curl -fsSL https://onyxresearc…
AnnouncementToday, Merge is live on ProductHunt. Please consider upvoting!Upvote Your engineers are reviewing more code than ever before.Merge lets you assess for it. With Merge, candidates review a PR, just like on the…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
AnnouncementToday, Merge is live on ProductHunt. Please consider upvoting!Upvote Your engineers are reviewing more code than ever before.Merge lets you assess for it. With Merge,…
In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified tool access through AgentCore Gateway, AgentCore Memory, and the Agent Skills open standard to rapidly scale policy digitization capabilities, while preserving transparency, version control, and human oversight.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
In this post, you learn how Cohere Health built a multi-tenant agentic architecture on AgentCore using AgentCore Runtime’s secure MicroVM isolation, unified tool access through Ag…
TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically investigates production errors in real time, reducing root-cause analysis from 15 to 30 minutes of manual work to under 60 seconds.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
TReNDS, a research center at Georgia State University, built an agentic AI pipeline on Amazon Bedrock and the open-source Strands Agents SDK that automatically investigates produc…
<p><strong><a href="https://www.404media.co/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</a></strong></p> There's a fun anecdote from Accenture (apparently via leaked meeting audio recordings) in this 404 Media piece from June 24th:</p> <blockquote> <p>“We’re seeing from some of the data internally at least that it’s actually not our engineers that are driving the token consumption. It’s a lot of the non-engineers that are doing some of those behaviors [...] you were talking about,” Justice Kwak, Accenture’s agentic AI strategy lead, said [...]</p> <p>Stuart Henderson, Accenture’s client group lead, interrupts. He jokes he hopes Kwak didn’t just convert a PDF into images and then into markdown files. “I’m learning that’s one of the big token chewers,” Henderson says. “Turning PDFs into markdown: is that right?”</p> <p>That’s when Kwak says that’s what Accenture’s own data shows.</p> </blockquote> <p>Maybe if Accenture figure out that PDFs are a <em>terrible medium for communicating information</em> they'll be able to push that message out to the rest of the business world too! <p><small></small>Via <a href="https://www.tiktok.com/@404.media/video/7654962124053171470">@404.media on TikTok</a></small></p> <p>Tags: <a href="https://simonwillison.net/tags/pdf">pdf</a>, <a href="https://simonwillison.net/tags/markdown">markdown</a>, <a href="https://simonwillison.net/tags/ai">ai</a>, <a href="https://simonwillison.net/tags/generative-ai">generative-ai</a>, <a href="https://simonwillison.net/tags/llms">llms</a>, <a href="https://simonwillison.net/tags/ai-misuse">ai-misuse</a></p>
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
<p><strong><a href="https://www.404media.co/the-tokenpocalypse-is-here-companies-are-scrambling-to-stop-spending-so-much-on-ai/">The Tokenpocalypse Is Here: Companies Are Scrambli…
Live agent visualization · Commit review · AI commentary Watch your agent work. An AI agent rewriting your codebase looks like scrolling text in a terminal. Agent Monitor shows you what it's actually doing…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Live agent visualization · Commit review · AI commentary Watch your agent work. An AI agent rewriting your codebase looks like scrolling text in a terminal. Agent Mo…
Chinese Model Kimi K3 Breaks UK AI Safety Institute Benchmark Evaluations By: Paul Kassianik and Yaron Singer Over the past few months we’ve been testing performance of various models for defensive security. The AI comm…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Chinese Model Kimi K3 Breaks UK AI Safety Institute Benchmark Evaluations By: Paul Kassianik and Yaron Singer Over the past few months we’ve been testing performance of various mo…
Anthropic’s most advanced artificial intelligence model used fake identities to deceive real people and try to plant malicious code during testing by Britain’s AI Security Institute (AISI) –– the latest example of an AI…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Anthropic’s most advanced artificial intelligence model used fake identities to deceive real people and try to plant malicious code during testing by Britain’s AI Security Institu…
This is today's edition of The Download, our weekday newsletter that provides a daily dose of what's going on in the world of technology. How ideas of a vast censorship network moved from the online fringe to Trump poli…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
This is today's edition of The Download, our weekday newsletter that provides a daily dose of what's going on in the world of technology. How ideas of a vast censorship network mo…
Three Tests to Run Before You Switch from LoRA to FullFT Kimi K3 on Fireworks: Frontier Intelligence You Can Own Blog Three Tests To Run Before You Switch From Lora To Fullft Three Tests to Run Before You Switch from Lo…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Three Tests to Run Before You Switch from LoRA to FullFT Kimi K3 on Fireworks: Frontier Intelligence You Can Own Blog Three Tests To Run Before You Switch From Lora To Fullft Thre…
DuckDuckGo, the free, independent web browser with the quaint logo of a waterfowl wearing a bow tie, just took a swing at big tech through a satirical stunt marketing campaign directly targeting AI-powered smart glasses…
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
DuckDuckGo, the free, independent web browser with the quaint logo of a waterfowl wearing a bow tie, just took a swing at big tech through a satirical stunt marketing campaign dir…
The AWS Generative AI Innovation Center built an automated system that uses constraint programming and custom tree search to determine, with mathematical certainty, when and how an NHL team clinches a playoff spot. The approach was validated against four full NHL seasons of officially published results.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
The AWS Generative AI Innovation Center built an automated system that uses constraint programming and custom tree search to determine, with mathematical certainty, when and how a…
Responding to an article by China’s ambassador to the UK, Prof Paul H Cleverley advocates shared openness standards, while Dr Claire Jenkins says British AI can offer a distinctive path Ambassador Zheng Zeguang rightly celebrates openly released AI models, and the Chinese labs behind Qwen, DeepSeek and Kimi have led the way – competition that benefits everyone, especially where models can run on modest hardware in the developing world (The future of AI hinges on openness and cooperation. China and Britain can gain much by working together, 30 July). But his claim that openness is a defining feature of China’s AI development deserves scrutiny. Take GeoGPT, the geoscience system from Zhejiang Lab showcased at last month’s World AI Conference as a model of jointly governed open science. It is promoted to countries as open, yet under the model openness framework – endorsed in a recent UN report – it would not qualify as open at all. It releases model weights (built mainly on Alibaba Qwen, whose licences are not Open Systems Interconnection-compliant), no training data or application source code is released, and its governance committee answers to Zhejiang Lab itself. Continue reading...
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Responding to an article by China’s ambassador to the UK, Prof Paul H Cleverley advocates shared openness standards, while Dr Claire Jenkins says British AI can offer a distinctiv…
Some of the biggest names on Google's AI team got new jobs this week. In some cases, including for legendary Googler Jeff Dean, those jobs are no longer at Google. Given that Google's models seem to be behind the best of what's coming out of anthropic and OpenAI, is this a sign of Google in turmoil? Is it about Demis Hassabis wanting something more interesting to work on than virtual assistants? Or is there something else entirely happening here? On this episode of The Vergecast, Nilay and David start by discussing the leadership shake-up at Google, the state of the AI race, and whether Google is actually set up to succeed here. They also t … Read the full story at The Verge.
AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
Some of the biggest names on Google's AI team got new jobs this week. In some cases, including for legendary Googler Jeff Dean, those jobs are no longer at Google. Given that Goog…