Upstanding Robot

Ask for what you want

Wed, 23 Sep 2026 00:00:00 +0000

There it is, the radical offering of 21st century computing, here at last: ask for what you want. It takes practice! And, honestly, a certain audacity.

Kalshi at the US Open

Thu, 10 Sep 2026 00:00:00 +0000

When asked about the rationale in this partnership, the USTA echoed its CEO’s statement on the matter: “Partnering with Kalshi gives us an opportunity to pioneer that next generation of fan engagement while ensuring the integrity of our sport.” A crucial part of the Kalshi deal, the USTA said, was being able to set limits on the types of predictions on offer: only bets on match results, as opposed to bets around umpire decisions, code violations, and player injuries.

This feels vaguely like blackmail on the part of Kalshi: “Partner with us or we’ll open up betting on all the worst things you could imagine.”

Project Chopin

Thu, 10 Sep 2026 00:00:00 +0000

A new side project from Github exploring collaborative planning with agents.

Kill the cookie banner

Mon, 31 Aug 2026 00:00:00 +0000

Kill The Cookie Banner is a consortium trying to influence the EU to update its data processing rules to make privacy controls a browser-level preference instead of a per-site preference.

Second brains

Sun, 30 Aug 2026 00:00:00 +0000

I’ve been thinking about second brains recently. Personally, I’ve got a version of llm wiki working with Obsidian. I’m also intrigued by Unicron, a project from Michael Angeles (aka Konigi). Michael’s approach adds some structure that I find appealing.

AI might be our best shot at taking back the open web

Tue, 31 Mar 2026 00:00:00 +0000

Mike Masnick:

The rise of agentic AI tools is opening up an opportunity to bring us back to that original world of wonder where you could just build what you wanted, even without a CS degree.

AI should help us produce better code

Wed, 11 Mar 2026 00:00:00 +0000

Simon Willison:

If adopting coding agents demonstrably reduces the quality of the code and features you are producing, you should address that problem directly: figure out which aspects of your process are hurting the quality of your output and fix them.

Shipping worse code with agents is a choice. We can choose to ship code that is better instead.

UI that's cheap

Wed, 11 Mar 2026 00:00:00 +0000

Marcin Wichary:

In my head, some bugs belong to categories that feel important, and yet remain hard to define and quantify: embarrassing bugs, dumb bugs, flow killers.

Somewhere in the hard-to-explain space is another tricky category: UI decisions that feel cheap.

My personal (least) favorite example of a cheap UX decision is when devs (and designers) don’t take the time to accept reasonable input into forms and force the user to input the data exactly the right way. For example, when jackson@example.com (note the extra space) isn’t accepted as an email address.

Home cooking

Mon, 09 Mar 2026 00:00:00 +0000

Rafe Colburn, riffing on a post from Robin Sloan:

Robin Sloan describes himself as the programming equivalent of a home cook. I’ve been working in professional kitchens for a really long time, but lately I’ve rediscovered the joy of home cooking myself.

Ditto.

Learning to use CLAUDE.md

Mon, 09 Mar 2026 00:00:00 +0000

We’ve been talking a lot at Viget about how to customize CLAUDE.md so I’m doing some reading this afternoon:

Learning the basics of CLAUDE.md
Learning the basis of writing skills
Checking out examples of skills from folks like jibbajabba, jackyliang, and obra

Simon is sharing advice on agentic engineering

Thu, 05 Mar 2026 00:00:00 +0000

Simon Willison is sharing patterns (and anti-patterns) for agentic software engineering

AI Is New And Cool

Tue, 10 Feb 2026 00:00:00 +0000

What makes the AI chatbots and agents feel light and clean, here and now in 2026? Is it an innate architectural resistance to advertising, to attention hacks, to adversarial crud? No — it’s that they are simply new! The language models in 2026 are Google in 1999, Twitter in 2009. Their vast conjoined industry of influence hasn’t yet arisen … though it is stirring.

Robin Sloan

Content Market Place, Coming Soon

Tue, 10 Feb 2026 00:00:00 +0000

Missed this news last week, but Microsoft is working on a content marketplace to help content creators license access to their content to AI providers. Now comes word from an AWS conference that Amazon is doing the same thing. This follows on the release of the “official” Really Simple Licensing spec which provides a way for content providers to communicate access and licensing terms for their content to bots. However, no bots I’m aware of have indicated they’ll support RSL. Google has made some noise about monetization tools, but I’m not aware of them pursuing something along these lines.

Obsidian CLI

Tue, 10 Feb 2026 00:00:00 +0000

Obsidian has a CLI now

Ted Chiang on AI & Capitalism

Tue, 03 Feb 2026 00:00:00 +0000

I tend to think that most fears about A.I. are best understood as fears about capitalism. And I think that this is actually true of most fears of technology, too.

Ted Chiang

Blogging with Claude Code

Wed, 21 Jan 2026 00:00:00 +0000

Last Spring I decided I wanted to re-start this blog and realized I could use it as an opportunity to get more comfortable with the new generation of AI coding platforms. I wrote about the experience on the Viget blog. I’ve also included the post after the jump for posterity.

Fri, 09 Jan 2026 15:33:48 -0700

Catching up on some reading today and came across this:

[Claude Code] has the potential to transform all of tech. I also think we’re going to see a real split in the tech industry (and everywhere code is written) between people who are outcome-driven and are excited to get to the part where they can test their work with users faster, and people who are process-driven and get their meaning from the engineering itself and are upset about having that taken away. (This is not to say that there aren’t many issues with AI aside from these things, of course.)

It wouldn’t surprise me to see more artisanal teams, startups, and small businesses spring up to give that second set a home. But I think we’ll also see more startups and projects created by the first set, too.

That’s Ben Werdmuller (emphasis mine), responding to Simon Willison’s recap of the year in LLMs (Simon also published some predictions for 2026)

Following

Thu, 31 Jul 2025 12:00:00 -0600

Daily feed reading habit

Mon, 28 Jul 2025 23:01:09 -0600

Going to start collecting different AI design metaphors. Drew Breunig described Gods, Interns, and Cogs. Geoffrey Litt is thinking about Copilots and HUDs.

Fri, 25 Jul 2025 12:44:09 -0600

Would love to see more documentation, like this March 2025 post from Google, educating content creators on how to live in the AI search future.

Thu, 30 Jan 2025 13:48:54 -0600

I love a good nerdy usability blog post (thx Baymard)

tl;dr: Dropdowns kinda suck except in very limited and specific circumstances.

Thu, 30 Jan 2025 11:46:42 -0600

Reuters made a little game about Cozy Games

Related, I don’t think I would have survived 2020 nearly as well without the Untitled Goose Game

Tue, 28 Jan 2025 18:27:47 -0600

Learning about DeepSeek today …

This great FAQ from Ben Thompson digs into why this is big deal, why it might be good in the long run, and also provides a nice background on different reinforcement learning approaches.
You’d be right to think DeepSeek, an AI model from a Chinese company, doesn’t want to talk about some things.
DeepSeek was surprisingly cheap to train and is very cheap to use (compared to similar models from OpenAI and Anthropic).

About

Wed, 30 Oct 2024 16:05:47 -0600

About

Designer, all around web geek. UX and design leader at Viget. Fond of breakfast burritos. Made this site to learn Claude Code and share interesting articles.

Wed, 30 Oct 2024 16:00:52 -0600

Drew Breunig:

After plenty of discussions and tons of exploration, I think we can simplify the world of AI use cases into three simple, distinct buckets:

Gods: Super-intelligent, artificial entities that do things autonomously.

Interns: Supervised copilots that collaborate with experts, focusing on grunt work.

Cogs: Functions optimized to perform a single task extremely well, usually as part of a pipeline or interface.