ariwilson

Weird to hear a full throated defense of the RIAA here

15 million dollars

My launch Switch 1 battery is still working. Capacity is probably 80% or less but it still works fine.

Maybe Claude is operating at a higher, self-improving level than all of us poor HN commenters. Wasting the local machine's resources to look pretty is a plausibly deniable way to make the Claude Code FE unusable with local LLMs, starving the competition.

zoom settings fucking suck to set up full AI summary / transcript btw. i know it's a one time cost but it's across every engineer

Have you learned anything interesting from your agent ant farm?

Android handhelds (e.g. AYN Thor, Odin 3, Retroid Pocket 6) have been becoming more and more useful for PC gaming via apps like GameNative and GameHub. See for example, Elden Ring: https://youtu.be/GlzMkqFmKjo?si=w9q-j2ntt154b0--&t=621

why not just use Plaid under the hood

I don't really get this; could just use Plaid and have your own transaction/net worth site/app in a few hours with Claude Code and it'd be much more consistent.

What's wrong with Express?

why do you think agents you make yourself will be better for you? integration with tooling that you prefer? your local dev setup built in?

curious as i haven't gotten around to writing my own agent yet

Very cool and works pretty well!

yes because a phone cpu cannot cool itself to keep at peak performance like a desktop processor can

This comment sounds like the basis for a nice Black Mirror episode.

Is it really inspired by love if you put 5 seconds into it?

I've done the AI books for my kids but putting effort into making them personal and interesting has been the main point.

why a mac mini rather than a cloud vps

Hi Kenton! I was the recent grad you handed this web app off to after you built it, so I expanded Jeff Dean Facts so that anyone could create and rate facts about anyone at Google :). There were a ton of team in-jokes added before I stopped working on it - O(5k) IIRC! :)

This web app was also how I learned the pain of maintaining a live web service with a lot of ever-changing dependencies. How I sighed when the AppEngine version changed and I had to fix things again...

I handed it off again before I left Google but I have no memory of who that was to unfortunately :(.

Compare this car to the Toyota RAV4 PHEV which in some ways is simpler than a gas powered RAV4 (no alternator, no transmission) but maintains the same ease of maintainability and cheap parts availability as the base RAV4 (makes sense, they sold >4M of them).

PHEVs are complicated tech so I figured I would choose one with a proven design (Prius -> Prius Prime -> RAV4 Prime).

I don't know Tai Lopez and he seems like an asshole based on his public persona but I think you'd be surprised by the number of (especially first generation) millionaires who will negotiate over pennies. The easiest way to have a lot of money is to earn a lot and not spend a lot.

I have a more nuanced take here. For low performing or junior employees, remote work was generally a terrible thing that led to less productivity (and more managerial overhead). For strongly performing employees with obligations at home, there were many who preferred working at home.

I fall more into the latter camp (at least I hope so) and, given I've only worked in nice offices with catered lunches, gyms, video games, offsites, etc, I enjoy a 3 day hybrid schedule works best for me.

Editing notes on the content - the content of this blog post is clearly AI-enhanced (emdash) which is ok but the tone is not. It's super flowery and oversold - example "It was a shift from a single laser to a powerful floodlight."

What is wrong about their claims?

No mention of product prototyping products e.g. vercel v0 or Firebase Studio. Those to me seem like clear 0->1 wins, especially vercel with their hosting/marketplace integrating well with AI-driven development.

Any ranking of states that ends with Mississippi is one I can get behind

when?

Cool article!

Is there value in adding an overseer LLM that measures the progress between n steps and if it's too low stops and calls out to a human?

I'm a great user for this problem as I just got a 3D printer and I'm no good at modeling. I'm doing tutorials and printing a few things with TinkerCAD now, but my historic visualization sense is not great. I used SketchUp when I had a working Oculus Quest which was very cool but not sure how practical it is.

Unfortunately I tried to generate OpenSCAD a few times to make more complex things and it hasn't been a great experience. I just tried o3 with the prompt "create a cool case for a Pixel 6 Pro in openscad" and, even after a few attempts at fixing, still had a bunch of non-working parts with e.g. the USB-C port in the wrong place, missing or incorrect speaker holes, a design motif for the case not connected to the case, etc.

It reminds me of ChatGPT in late 2022 when it could generate code that worked for simple cases but anything mildly subtle it would randomly mess up. Maybe someone needs to finetune one of the more advanced models on some data / screenshots from Thingiverse or MakerWorld?

Why?

If you work 8 hours a day on Saturday and Sunday and each line has on average 40 characters, then on average you have to type about 5 characters a second to hit 7000 lines of code.

There's some heavy assumptions about boilerplate or autogenerated code going on in that estimate, as I don't think very many average 5 characters a second over 16 hours.