paid_dot_expert

If we are going down the rabbit hole - I like to use groups as my "tookmarks" or "babs" so to speak. They act like both and help to keep things organized by project. Bookmarks are for permanent things, e.g. for work it might be direct deep links to things for the service(s) your team operates, and groups for projects e.g. this quarter we are adding spinners to the fidgets, and then regular tabs for the ephemeral, e.g. googling why ain't Docker decking the ducks.

SPXEW ftw

Cress is a word I haven't heard in decades. Got to get some cress!

It also creates a human feedback loop. It will train you to instinctively not keep old tabs open as you need to deal with the plants.

You are both right.

Your username checks out. Time to shine?

I find AI generated language hard to understand when it is "in it's own world" and it knows what it means but can't articulate it without buzzwords and slop. A follow up "ELI5" type of prompt often sorts this out. Seems like a failure mode and you need to snap it out sometimes. Opus 5.5.

Try pause for 3 seconds in your favourite harness

Well a family could easily get through 4kg of meat a week

Ok Ok. Lemme convert that.

One kilo of beef is roughly equal to 8 kilos of pork, 10 kilos of chicken, and 20 kilos of tofu in CO₂ emissions.

First through as I read this: Microservices.

> This essay introduces the concept of decoherence: the accumulation of locally valid but mutually incompatible or redundant models within a system, such that the cost of change is dominated by translating among those models and preventing unintended side-effects.

But then famous last words:

> The good news is that this rules out the specter of runaway recursive self-improvement, the intelligence explosion that goes parabolic before anyone can react, as decoherence both prevents AI from improving in a bubble and limits the rate at which it can improve outside of it.

After the OpenAI/Huggingface and similar I am not so sure. Even if that was a publicity stunt of sorts, I think it shows they can go off the rails. Today it is hacking, but tomorrow it may be training a smarter model to join their cohort, without us being involved.

Good lesson to fact-check even the things we "know" when writing.

That is what I mean, apologies for not being clear.

Sort of. What if you asked your second agent to fuzz test the work of the first agent, adversarial code review, or make a video to explain all the code.