luckystarr

I think the problem in the machine is "investors" as they have primarily a capital based value evaluation.

Nothing else has value to them apart from capital and its "profitable" usage, so the fundamental reason why corporations even exist, to collectively bring about real world value takes a back seat.

Does that include the disinformation infrastructure? If so, they should keep it on.

Over 20 years ago we had a doom in which your processes were represented by monsters and killing them sent the kill signal. :)

They still have enough unskilled labor they can pull from the country side. They pack up the village and ship them (relocate the people) to a city in need of workers.

Finally. Now I can remove all my symlinks. :)

Consider: the US is a (somewhat) greenfield project, while the EU is a brownfield refactoring.

These sorts of refactorings take time, even more so if done by "committee". The good thing is that explicit interfaces have to be created thereby (hopefully) increasing adaptability and resilience over time.

Why would one need a blackboard if one had a coordinating agent that would launch a sequence of builder agents that run either in parallel or in sequence depending on what the coordinating agent determined was safe?()

Honest question, I don't really get how this would improve my work flow.

() Spec and (variably coarse) implementation plan are already grounded in code reality and are commited.

Translation: As the number of bugs per line of code is a constant depending on language and project, we will experience a world full of bugs now that LLMs generate so much more code. On the other hand, LLMs are so quick at fixing them, the number of bugs should go down.

I wonder which trend will be winning though. I personally won't bet on quality.

I noticed back in the days that my FidoNet point client software ran a lot faster (actually processing a lot of messages, so IO and CPU heavy) in Windows than in DOS, which was unintuitive to me back then.

What was the minimum required density you derived?

Not if the models are way cheaper. For many tasks you can do with DeepSeek Flash, and for more gnarly problems you switch to GLM or Kimi. But sure, if you do everything in large models like Kimi K3 or GLM it gets expensive quickly.

Until the manufacturers enter an arms race and copy a page out of the mobile hardware vendors book. But perhaps they'll do it badly and we've got a few more years.

Apparently the task was to remove dead weight. Haven't read what they replaced "Enzyme" with.

I did subagent based removal tasks a few times. These were the ones that required the least amount of input or thinking from me, because the requirements are abundantly clear. "Remove this part of the code without breaking any other part or by porting the tests done with it onto another system."

In these situations the code acts as the bookkeeping ledger itself, and coordination complexity is almost a no-brainer.