svaha1728

I'd guess they have a lot of internally facing tooling for monitoring, one-shot eval to catch people prompting bad things, etc. That stuff can probably be yolo'd and it just annoys the internal teams using it.

I expect a “Prettier” for AI generated text in the near future.

If you are interested in Zanzibar and Relationship-Based Access Control (ReBAC) it’s worth taking a look at OpenFGA https://openfga.dev/

On a music blog, yes! Now go try to rewrite the firmware for your car.

Kyla Scanlon is speaking from personal experience. It can be a great school if you put in the effort. Will the market will reward that effort with a job? Maybe.

Working in microgrids and I completely agree. I use Claude Code every day. There’s so much we don’t know and so much that an LLM is not going to help you with.

It depends on the job. T-shirts yes. I enjoy building microgrids. There are many unsolved challenges. When the robots start doing it maybe it’ll be boring. That’s a long way off.

I don’t see a compelling reason for Apple to jump into the AI game. The MacBook Pro M4 is a dream to work with, and it works great with Claude Code. Creating quality products is a niche market, but that strategy still has merit.

I grew up in the Amiga era when we would type code from magazines to write games. I learned a ton debugging those programs.

It's safe to say at this point. The more Microsoft relies on Copilot to solve its security problems, the more problems Microsoft will have.

The Microsoft tech debt dumpster fire continues.

I completely agree with the author's comment that code review is half-hearted and mostly broken. With agents, the bottleneck is really in reading code, not writing it. If everyone is just half-heartedly reviewing code, or using it as a soapbox for their individual preferences, using agents will completely fall apart as they can easily introduce serious security issues or performance hits.

Let's be honest, many of those can't be found by just 'reading' the code, you have to get your hands dirty and manually debug/or test the assumptions.

If he reiterates that comment to me after two beers in a relaxing bar I might believe him.

I was thinking that too. He's a great programmer, and at this point I can't imagine he's having fun 'prompting' an LLM to write correct code.

We wanted Aaron Swartz and we got Sam Altman.

Yes. Don’t take a screenshot of your teams meeting, you aren’t trustworthy. We will block that while we take a screenshot of everyone’s computer every couple minutes and run an LLM on it.

Nice simple project to start with kids. I'm always looking for something for kids that is fun and not overwhelming. I wish GitHub Copilot would make a 'Family Plan' :)

When I was young I got to meet a lot of the aging jazz musicians of the 1930s in Kansas City. It absolutely was a career here. Granted, that’s a distant memory for most people.

If X, AWS, Meta, and Google would just dump their code into a ML training set we could really get on with disrupting things.

I'm loving Claude, is there a good VS Code integration tool that isn't Github Copilot?

Not even close. I’m a programmer but also a guitarist. I love asking it to tab out songs for me or asking it how many bars are in the intro of a song. It convincingly gives an answer that is always way off the mark.

As long as you can constrain your solution to the logic contained inside a Todo app, all is golden /s

I’ll miss Guitar Techniques. I feel like they missed the boat and should have integrated with Soundslice…

YouTube has some great players, but I’d often search for guitarists from Guitar Techniques that YouTube algorithms hadn’t played for me yet.

rm -rf and start over with better prompts /s

True, but it’s harder to run around with a begging bowl in Western cultures. Even though self worth is an illusion, right livelihood is part of the Noble Eightfold Path.

Boeing is far from an anomaly. They’ve just reached the stage where it’s noticeable.

I cringed when Musk embraced lithium-ion batteries for grid storage, there were better chemistries out there that got ignored. Guessing it set us back 20 years for that application.

Because we chase after cost minimization over aesthetics and craftsmanship.

Every now and then I can provide good feedback when I pull down the branch in question, test it locally, and try to think of a way to break it. Rarely do I have that kind of time.