Viewing profile — macrolime

GPT-5.6 Sol’s detected cheating rate was higher than any public model we have evaluated on our ReAct agent harness. For our task suite, we define “cheating” as behavior where the m…

Most consistent way of achieving it I've managed is use a watch with an alarm that vibrates and is trivial to turn off or turns off by itself, then set it to go off after sleeping …

I had something kinda similar happen to my hotmail account. While I didn't lose access to it, I lost more than a decade of correspondence dating back to my teenage years. The reaso…

I find that surprising. GPT 5.2 is the model I've had working the longest. It frequently works more than 4 hours nonstop, while earlier models would stop to ask if they should cont…

"Can you replay all of your prompts exactly the way you wrote them and get the same behaviour out of the LLM generated code? In that case, the situation might be similar. If that's…

So you're saying machine code is public domain if it's compiled from C? If not, why would AI generated code be any different?

So it's made of extraterrestrial bubblegum, got it.

Pretty sure it will beat Sonnet by a wide margin in actual real-world usage.

I've found that SDD is actually what you need to be able to work with code bases when they go above around 100 000 lines of code. It's what unlocked getting LLMs to work well with …

In the EU you can also generally look up the cost, even in cases where the patient doesn't pay, there is a bill and fixed costs. The costs are what the government pays or what a fo…

What is "it". Gpt-5 auto? Gpt-5 pro? Deep research? These have wildly different hallucination rates.

Voice control is much much much worse than touch screens. You have to try 10-20 times to spell out a command before it maybe does want you want, and that is if you're incredibly lu…

This is my experience too. Make agents for tasks, not roles. I've seen this for coding agents using spec-driven development for example. You can try to divide agents into lots of d…

YouTube videos of birds?

I mean copying from the iOS app.

Seems copying text in the app doesn't work? In that case it is useless. A quick way to copy an entire chat and a selection messages is a requirement for me to be able to use it.

Thing is that it took 10-15 years for the stocks of these companies to reach the same marketcap again.

If it's so hard, then why are there multiple open source projects that are just as good?

You can use Claude Code as a provider if you want it subscription based https://docs.cline.bot/provider-config/claude-code

I ssh into my server, then use the devcontainer cli tool to open a shell in the dev container. Found that easier than installing ssh in every container, especially when there's lot…

Yeah, it's like an idiot savant intern who has memorized all the API docs in the world, but still somehow struggles to work independently.

I like using Claude Code through Roo Code (vscode extension). I find it easier to work with text using a mouse, vscode diff viewer etc. I guess if you're very good at vim shortcuts…

Personally I use dev containers on a server and I have written some template containers for quickly setting up new containers that has claude code and some scripts for easily conne…