FeedCity

In the early 2000’s, my parents took us on a road trip to Glacier National Park in Montana. We made the journey in our new (used) family van: a green Dodge Caravan whose reputation was soon to become “a lemon”. I was a teenager and didn’t pay a lot of attention to the detail...

H8, PA-RISC, and SuperH

Je samenleving, overheid en maatschappij overlaten aan Amerikaanse servers komt met twee problemen: Alles werkt alleen zolang ze het in Amerika goed vinden. Met een enkel briefje op Whitehouse.gov lig je uit hun cloud. Via minstens drie wetsinstrumenten gunt Amerika zich toegang tot onze data en communicatie, ook al staan de Microsoftservers in Europa. Dit is allemaal heel vervelend, en er is ook weinig aan te doen. Geen enkele “speciale” afspraak heft de realiteit van Amerikaanse wetgeving op.

Anthropic are the only major AI lab to publish the system prompts for their user-facing chat systems. Their system prompt archive now dates all the way back to Claude 3 in July 2024 and it's always interesting to see how the system prompt evolves as they publish new models. ...

Figma's reliance on non-designer seats made it uniquely exposed to AI. Claude Design's launch deepens the problem.

Research: Claude system prompts as a git timeline

Anthropic publish the system prompts for Claude chat and make that page available as Markdown. I had Claude Code turn that page into separate files for each model and model family with fake git commit dates to enable browsing the changes via the GitHub commit view.

Tags: system-prompts, anthropic, claude, generative-ai, ai, llms

Before GPS, how did aircraft navigate? One important technique was celestial navigation: navigating from the positions of the stars, planets, or the sun. While celestial navigation is accurate, cannot be jammed, and doesn't require any broadcast infrastructure, it is a diffi...

Today's links Georgia's voting technology blunder: It's possible for Dominion machines to suck, but not in the way that Tucker Carlson says they do. Hey look at this: Delights to delectate. Object permanence: GWB's illegal iPod; McDonald's breakfast sandwich fanfic; Technofeu...

Agentic Engineering Patterns > Here's an example of a deceptively short prompt that got a lot of work done in a single shot. First, some background. I send out a free Substack newsletter around once a week containing content copied-and-pasted from my blog. I'm effecti...

This year's PyCon US is coming up next month from May 13th to May 19th, with the core conference talks from Friday 15th to Sunday 17th and tutorial and sprint days either side. It's in Long Beach, California this year, the first time PyCon has come to the US West Coast since...

Most anti-AI rhetoric is left-wing coded. Popular criticisms of AI describe it as a tool of techno-fascism, or appeal to predominantly left-wing concerns like carbon emissions, democracy, or police brutality. Anti-AI sentiment is surprisingly bipartisan, but the big anti-AI ...

Speed has become the primary virtue of the modern world. Everything is sacrificed to it. Move fast (and break things, not as a goal but as a consequence). Wisdom requires allowing yourself to be undone by experience: An opinion dismantled by reality. An artifact torn apart ...

This series of articles chronicles the history, both real and pseudo, behind Gabriel Knight 3: Blood of the Sacred, Blood of the Damned. The Holy Blood and the Holy Grail was published by Jonathan Cape in Britain on January 18, 1982. Delacorte released an American edition five weeks later, under the punchier title of simply […]

Today's links Tiktokification shall set us free: Zuck keeps accidentally freeing his hostages. Hey look at this: Delights to delectate. Object permanence: B2B Trotsky; Public service games; NZ 3 strikes rule; Snowden, vocalist; Obama says money compromised him; Bullshit trees...

Release: datasette 1.0a28 I was upgrading Datasette Cloud to 1.0a27 and discovered a nasty collection of accidental breakages caused by changes in that alpha. This new alpha addresses those directly: Fixed a compatibility bug introduced in 1.0a27 where execute_wri...

I love cutting-edge tech, but I hate hyperbole, so I find AI to be a real paradox. Somewhere in that whole mess of overnight influencers, disinformation and ludicrous claims is some real "gold" - AI stuff that's genuinely useful and makes a meaningful difference. This blog

Release: llm-anthropic 0.25

• New model: claude-opus-4.7, which supports thinking_effort: xhigh. #66
• New thinking_display and thinking_adaptive boolean options. thinking_display summarized output is currently only available in JSON output or JSON logs.
• Increased default max_tokens to the maximum allowed for each model.
• No longer uses obsolete structured-outputs-2025-11-13 beta header for older models.

Tags: llm, anthropic, claude

Many of you follow this blog because of the regular features about electronic circuit design.

For anyone who has been taking my pelican riding a bicycle benchmark seriously as a robust way to test models, here are pelicans from this morning's two big model releases - Qwen3.6-35B-A3B from Alibaba and Claude Opus 4.7 from Anthropic. Here's the Qwen 3.6 pelican, generat...

It’s rare that you get to see work that directly helps those who most deserve it, but I want to tell you about the opportunity we so seldom get to actually contribute in a way that we know will have real impact. I’ve been on the board of the Lower Eastside Girls Club for abo...