bradgessler

Apple's displays are great if you want to have the flexibility of a Mac mini. They're expensive as hell, but overall a great display if you want to plug something into a Mac and not have to fuss around with cables, etc.

The constant has always been tools that maximize developer productivity. What's changed is that LLMs are now the best way for developers to tell machines what to do. We've all been given a much bigger lever we can use to spend our waking hours (and even sleeping hours if you run agents overnight) to move even bigger mountains.

The solution is legal and political, not technical.

I'm sure KYC is next.

When building web apps, I prompt humans and AI with “the best design is accessible design” and start from there.

It always ends up being faster, clearer, simpler, and better.

I asked Borris at an Anthropic event in SF this week why Opus 5 and Fable 5 seem to forget so much when I give it rapid fire tasks when I'm reviewing a UI or something. He told me to run in safe mode, which didn't help at all.

My tinfoil hat theory is Anthropic is trying to get their new models to take on higher-level longer-running tasks, which has a trade-off against rapid-fire tactical use of an LLM.

For these reasons, I've always found the 5 series models from Anthropic aren't great and use 4.8 for a lot of my work.

I'd like to see real numbers that compare Docker Desktop for macOS before microVMs to post-microVMs.

I stopped using Docker on macOS because host file system performance was so slow, even with all of the caching hacks piled on top of it, that it made the whole thing effectively unusable for development.

Directionally the post shared sounds great, but it seems "too good to be true" that we'd have a performant microVM for macOS.

Human Code Dump → AI Code Dump

Also, water is wet and the sky is blue.

What happens when the backup breaks?

Reminds me of an “all you can eat” buffet I was at once where the owner told me, “that’s it, that’s all you can eat” and cut it off.

I got og.plus that expands to OpenGraphPlus.com.

At first I was stoked to have a two letter domain, but then I looked into it and learned these companies will get you hooked with a low initial price, then jack up the prices as the domain becomes established.

Quite the grift. My plan is to tread lightly on that domain and be ready to back away from it when the rent seekers move in.

You’d think there would be some sort of rules to the neutrality of these TLD administrators, but nope.

The second time around I wised up and go ogplus.net for an API domain instead of ogplus.media. I’ll take neutrality over vanity any day.

I’m super early stages with this project and exploring what it would look like agents were just unix programs running securely along side other Unix programs. A big benefit of that is I can pipe one agents output into another agents input.

Another idea I’m exploring is having agents write code for simple tasks. First example, if you run “hello world” with agent script, the first time an agent reads the text file, understands its simple, then writes a static memory.js file. When the program runs again, it hits that file and never invokes the agent.

Where things get interesting are the cases where a script works for some cases, but not all. When that happens, the memory.js script can call agent.resume() during a static run so the agent can take over.

I remember thinking Google paid an absurd and ridiculous sum of money when they acquired YouTube. I couldn’t have been more wrong, what an incredible acquisition.