MrBuddyCasino

I was using it via OpenCode and OpenRouter. What setup do you use?

Gemini search isn’t great by default, but Deep Research gives noticeably better results.

Spoiler: its probably fraud.

An I the only one who was disappointed with GLM 5.2 after all the hype? It was thinking forever and sometime just stopped mid task.

Uh snap it indeed is cheaper: $0.20 / $1.20 vs $0.30 / $2.50. Gemini is mostly good enough for what I do with it, but the cost savings are interesting. Gemini is still faster though. Not su…

Yes this is my impression as well. To be fair I didn't compare to Luna yet, but Gemini 3.5 Lite is a very good and cheap multi-modal data extraction model.

I like using 3.5-flash-lite for doing cheap PDF and Image data extraction stuff. I don't think there is a better bang / buck model right now (3.1 is cheaper but a lot worse).

Look at the average React site in the wild, and notice that it is dog slow due to the various performance bugs it exhibits. Apparently nobody can get it right.

Yes I don’t see the appeal of HTMX in most cases. Vuejs has less footguns than React, and LLMs can produce it decently well to at least get started and then refactor.

It is also not annoying to use. It doesn’t overcomplicate things, and its quick. Much better than eg GLM 5.2. Pretty good bang for the buck.

The same demographic is against building new power plants, especially in their vicinity. There could have been abundant power if Nixon‘s plan to build out nuclear had been allowed to proceed. Now Chin…

This does not bode well for American prosperity. This is going the way of Europe, complacent and non-competitive. The future belongs to China.

Its not even true. Paradoxically they lower power bills.

Well said. It is not without merit, but tends to attract the tedious killjoys and midwits. The bureaucrats who above all value process over outcome.

Mandatory link: the Zarelli soundtrack, using Leonard Nimoy's reading. https://open.spotify.com/track/0DflgiMYRQP3UXtZ47NBus?si=XGR... …

This is great. It focuses on utility and information density over design. It looks like someone took a terminal UI and transplanted it to the web, Bloomberg terminal style. I'm pretty sure you ca…

> In general, they trend towards complicated APIs which focus on Traits, safe abstractions, Async etc. My pref: Use Rust as a nice overall language, and write low-friction APIs, vs the abstraction…

Agreed but apparently BigCorp hasn’t gotten the news yet.

Today it is a great language with a runtime that is unequaled. For heavy duty business backend server load, it is the standard choice, and rightfully so. Do I love Spring? No. Do I prefer Typescript f…

> If you create 3 buckets of inference pods, say, 256k, 512k, and 1M, then you have to worry about filling/dynamically-scaling all of them. That seems like it is not an awfully hard problem,…

AI infra buildup is so massive that the frontier labs should be able to offer more than one level of context length to incentivize token thriftiness. One would think compute-constrained actors like An…

It would still be nice to mark them.