Viewing profile — glub

You're making a lot of assumptions, projecting, maybe? I do have dedicated machines and dedicated VMs for agents. RCE on a VM is still a RCE.

Just a few years ago, people would lose their marbles if some software installed a background agent to send you notifications or something. Now we agreed that it's totally normal t…

Tested muse spark 1.2 because it was rated so high on design arena, and I've missed a model that can do nice UI in the hands of an operator with no UI skills. It produced worse UI …

It's also starting to go beyond reasoning and it's becoming much more problematic. Reasoning is one thing, but codex, for example now encrypts agent-to-agent messages as well, and …

GLM subscription is better than API, but significantly worse than Codex, even when used outside peak hours.

If anything, it's going to be more expensive. Price/performance ratio isn't there yet for frontier open weight models. But regardless, you definitely should use a harness where swi…

I've tested GLM 5.3 on the release day and Artificial Analysis is spot on. It's a really good model. But my main takeaway was something else. I've used closed weight models for lon…

Yeah, for web apps, you can trick models by simply proxying it and pointing the models to that localhost. They then think they're not working on a live target. Have personally test…

Is this about the new project Blue and Red thing? Or just pre-existing Trusted Access for Cyber program? I've joined TAC, but still have to dance around it.

Code owners - no. Ultra wealthy code owners with connections, and a few peasants with popular projects, for public image.

No, you can give the model same prompt and it will give you a similar compaction result. On the backend, that's precisely what happens. There's nothing else going on in that encryp…

The only "secret" there is a very basic instruction that the model receives, like "summarize current state and upcoming work" before compaction - same model that was just running y…

I did this with Codex's recent encryption of compaction. Interestingly, I didn't have to drop to a dumber model, just a 2 sentence prompt auto-injected before and after compaction …