PestoDiRucola

Maybe. On the other hand, maybe the reason models aren't good at writing yet is because the labs don't think it's useful or profitable (yet) to focus on training models for writing prose.

Holy mother of whataboutism.

> What is a Russian citizen supposed to do?

Who cares. Their government started this, and by all accounts most of their population supports, or is indifferent to it. They made their bed and they can now lie in it.

> So at the breaking point, will Russians storm the capital or storm Ukraine?

They've been storming Ukraine for the past 4 years now.

Production has a critical error and we need to push a fix while our whole build pipeline runs on GH CI. Which is not working. Thank God their critical parts never break.

Why would I use something inferior to emacs in the first place? :)

Not even for the average person. Luna is an amazing model for most coding tasks.

> will be inseparable from humanity and/or have the means to replicate

How will this happen if you need insane amounts of compute to run these models? Where will the models replicate themselves by taking up PBs of space without anyone noticing?

> You and the AI agree on an outline or other high level representation, then the LLM expands it into a document.

What a horrible, cold, inhumane world that would be.

What makes you think that models will improve with the same pace that they have been improving in the past few years?

1. Ruthlessly keep PRs small (use stacked PRs if needed)

2. Very strict CI (tests, linting, if you can afford it an agent to review the code)

3. Related to the first point, but simply refuse to review PRs over a certain number of lines of code (within reason, some PRs cannot be split into smaller ones)

I think you're giving the claude code team too much credit. I don't think that's a feature but something that probably got vibe slopped into the harness by claude

> because every other form of media is trash

Not trying to be controversial, but do you also think forums such as this one are trash?