Kurtis Welch

@chris_grant @lifeisbutuful @claudeai @grok Exactly. Idk how they can justify charging $20 per month just to save someone a few hours a week. Don't they know I can just exploit an offshore exec assistant to do a worse job for the same thing at 5x the cost?

@lifeisbutuful @claudeai @grok Claude is expensive AF that’s how lol

Claude is built to be a genuinely helpful assistant for work and for deep thinking. Advertising would be incompatible with that vision. Read why Claude will remain ad-free: anthropic.com/news/claude-is…

I had an idea earlier this week for a self-improving AI architecture. I've been spending evenings this week designing it, and I finally had some time this evening to spin up 25 AI agents to build it. This is actually an iteration on a project I built last summer. The original project is called Flows. It took me about 6 weeks to build it - and I still use it all the time. This new iteration, called Routines, is significantly more complex. I spent probably 4 or 5 hours this week fleshing out the architecture for the project. I spent about 2 hours yesterday evening architecting the agent swarm to build it. Now I'm about 6 hours into managing the bots that are building the project. Essentially I'm checking in on them every 5 or 10 minutes, manually moving them through check points so I can keep tabs on the project. Issues I've run into: - I had to completely wipe the last module because the instructions the coding bot was given were pretty terrible. I had the master bot rewrite the instructions, and it performed vastly better the 2nd time - The AI *loves* to write things like `// TODO: implement this`. I have to prod it to make sure it doesn't get lazy - When writing the last module I realized a flaw in my architecture. This wasn't an AI error, but I had to go back and refactor one of the first modules to make everything work. Aside from that, it's been pretty smooth sailing. The agents are still chugging along as I type this, doing their coding, testing, documenting, and reviewing loop. The end is in sight, though! It's currently working through the final integration tests. Tomorrow I'll get to start building some routines and see if the architecture is actually effective. Tonight I'll sleep well knowing I didn't have to spend 2 months building this. If you're a software engineer and you want to learn how to use those same techniques I'm using to spin up a bunch of agents to write code for you, shoot me a DM. I'm hosting a series of classes this month to teach engineers how to build and use their own AI tools.

The end result is that it took me 15 minutes longer than if I hadn't added the blank line. And it's something that I wouldn't have done if I wasn't using AI. Does that mean that AI slowed me down in this specific instance? Or did it give me leverage to be more thorough?

Me: 30 seconds to type a prompt Agent: 5 minutes to write, build, debug, test Me: 10 minutes to review, test, commit the code Start to finish, we're 15 minutes in, for a feature with a tiny impact on the end result.

Example of why "ai coding is slower" is stupid. #vibecoding #metaengineering I have code writing a long list of products to a YAML file, which I will feed to an LLM. But, to help the LLM see those products as separate entities, I want a blank line between products in the YAML.

Made this: unclassified.news It's a strategic conflict analysis site that aggregates news and information on the Israel / Iran conflict and does scenario analysis and strategic assessment of the situation.

LLMs are capable of so much more than writing CRUD code. Just had a RecursiveAI Agent write enable headless agents on the RecursiveAI Agent platform. Took all of 5 minutes. Zero bugs.

The biggest mistake people make with AI is thinking it's plug and play and the results are what they are.

@simonw I'm most curious how the pricing shakes out after taking caching into account. Claude's cache pricing is complicated, but is very powerful when used properly.

My notes on Gemini 2.5 Pro pricing - it's cheaper than both GPT-4o and Claude 3.7 Sonnet I've also updated my llm-gemini plugin to add support for the new paid model simonwillison.net/2025/Apr/4/gem…

@sethrose Do you actually understand the economics of any of this? Or do you just wish it was free because tens of hours of YOUR time is entirely worthless?

OpenAI: "Non-profit" btw 😇 Translation: Let's lock the real o3 behind a $200/month paywall 💀 Plus users get o3-mini? Enjoy your scraps. You’ll never see the latest models again. This is why open-source AI (DeepSeek, Mistral, Llama, etc.) matters. 💯

@dillonloomis @Tesla_Optimus Except in the video the "autonomous" tag in the top right disappears for the stairs clip

@Tesla_Optimus Stairs?! And none of this is teleopetated 👀 The progress really is crazy 🎤🫳🏻 after the criticism from 10/10

Navigating by myself

@Moz Having a "display name" in the signup flow that has to be unique threw me off. Calling it a display name made me think it was just like the name you wanted to show to me on the dashboard. Calling it a UserName is a much more common convention and would cause less sign-up friction.

@HookEmHorns2034 @propjoesays You win.

@propjoesays I’m calling it - I’m saying A&M wins this week

aye given how this year has gone we beat bama we’re all getting A&M tattoos right?

Passwordless login (via email) *and* a place to store user data – with barely any lines of js. Looks… perfect? uthentic.net/documentation/…

I liked a @YouTube video youtu.be/J5_bnZX5CHA?a "I'm Scared," Songs About Emotions by StoryBots

@TheDaniPlay @GetSpectrum I pay $100/mo. They are offering a bundle (cable + internet + phone) with an intro price of $90/mo for the first year.

Most unethical ad I have ever seen. "No intro offer" "No big promises" Blatantly contradicted an inch away. @GetSpectrum

.@ChaseSupport I did, though it's depressing that Chase's response to people recording & publicizing awful calls was… prohibiting recording.