Flux
Quoting Ted Sanders

Quoting Ted Sanders

In general, LLM performance is incredibly multidimensional. There's no guarantee of a fixed ordering where the model that is best at math is also the model that's best at jokes. Despite that complexity, much of the variation in performance is explained by just a single variable: model size. In general, models that are bigger will (a) be more performant / reliable, (b) cost more per token, and (c) have better recall of esoteric facts. As you note, our models are ordered: Luna < Terra < Sol…

Simon Willison's Weblog
GitHub Octoverse 2026

GitHub Octoverse 2026

GitHub Octoverse 2026 I'm at GitHub Universe today (GitHub gave me a free ticket through their "GitHub Stars" program). EVP Jay Parikh just announced this year's Octoverse report, and highlighted these numbers in particular: This is a pretty stark representation of the impact of agentic engineering on GitHub. In 2026, merged pull requests tripled in less than a year to 220 million per month. Commits more than tripled to 7.38 billion per month, with most of that increase in the second half of…

Simon Willison's Weblog
The PHP Incident

The PHP Incident

The PHP security incident is now (almost) old news. The timeline looks something like this: In late August, Wiz Research discovered two serious remote code execution vulnerabilities in PHP called PHP2Shell. They reported the vulnerabilities to the PHP team on August 24, which started working on fixes on September 21. Amazon apparently detected PHP2Shell in […]

O'Reilly Radar — AI/ML
The October inflection point for vibe game development

The October inflection point for vibe game development

I've written before about how November 2025 was an inflection point for coding agents - the point where Opus 4.5 and GPT-5.1 crossed a tipping point that meant their respective coding agents became reliable daily drivers for software engineers. I think we've reached a new inflection point in October 2026, and this time it's for vibe coding computer games. Tree Appreciator Emberwick Battle Drones Pumpkin Farmer, aka Quarter Sun Cove Four times as insulting What happens if someone actually puts…

Simon Willison's Weblog
Are You Getting Your Money’s Worth From AI?

Are You Getting Your Money’s Worth From AI?

The following article was originally published on James Shore’s Successful Software blog and is being republished here with the author’s permission. Software development has emerged as the biggest beneficiary of AI automation. One CIO I talked to recently, with 170 people in his organization, measured a 2.1x increase in productivity from AI. That productivity came […]

O'Reilly Radar — AI/ML
Quoting Terk Terkowitz

Quoting Terk Terkowitz

If your work does not benefit from current AI tooling, that is a finding, not a failing. Document why, share it with your community of peers, bring it to your manager, and work to find solutions. An engineer who can explain where AI does not yet help their work is demonstrating the judgement we are asking for. — Terk Terkowitz, An update from Amazon engineering leadership on the role of the developer in the age of AI Tags: amazon, generative-ai, agentic-engineering, ai, llms

Simon Willison's Weblog
Game Boy Color on My Conference Badge

Game Boy Color on My Conference Badge

Game Boy Color on My Conference Badge I'm at GitHub Universe this week and, similar to last year, the conference badge is a full-blown color screen computer. I've been hacking around with it again, and then I ran into with Steve Francia... who worked with Gemini to get a full NES emulator working on it, and then went a step further and deployed an emulator for both the Game Boy and the Game Boy Color. Which means, if you can obtain the ROM, you can run The Legend of Zelda: Link's Awakening on…

Simon Willison's Weblog
Are agent harnesses dying? What harness distillation changes.

Are agent harnesses dying? What harness distillation changes.

The following article originally appeared on The Arize Blog and is being republished here with the author’s permission. Every time you think you’ve just got the hang of this AI thing, another thing gets declared “dead.” This week, it’s agent harnesses. Back in ancient history, aka June, I wrote a piece called “Frameworks are dying, […]

O'Reilly Radar — AI/ML
GPT-6.1 Terra

GPT-6.1 Terra

GPT-6.1 Terra It's always interesting to note which aspects of a new model are emphasized in the release announcement. In the case of GPT-6.1 Terra, OpenAI went with visual reasoning and computer use: We’re introducing GPT-6.1 Terra, a fast, efficient model that combines detailed visual reasoning and precise computer use alongside clearer, more natural writing. A significant step up from GPT‑5.6 Terra, it excels at the communication and computer-based tasks that fill the workday, from drafting…

Simon Willison's Weblog