> The trick is to not have a bank account in your name only, you have it joint with a child/spouse and they can't take your money.

Yes they can take 100% of your part of that bank account which amounts at total / # of owners.

If people lack sense of humor or satire, even if pathologically, well, too bad for them. Why should the rest be denied of that satire? It's not harming anyone at all.

Unfortunately it's not too bad for them, it's too bad for everyone they're around. They aren't the ones that lose out when we start dismantling open source communities.

PP's point is that 2025-2026 is exactly the result of satire being weaponized to cause real harm, because people pretend it's truth.

That wasn’t people weaponizing satire, that was people just making weapons

> I want to be able to run the same spec again and see the LLM add a feature that I never expected (and wasn't in the last version run from the same spec) or modify tactics to accomplish user goals based on changes in technology or availability of new standards/vendors.

Be careful what you wish for. This sounds great in theory but in practice it will probably mean a migration path for the users (UX changes, small details changed, cost dynamics and a large etc.)

> If you're being emotional, it can detect that and rewrite your comment to be less confrontational and more constructive

Are you learning something in the process? does ti have your full emotional context, beside the full conversation context? There are probably many bade side-effects if people would actually start doing what you mention at scale.

One thing is computer code, which is an intermediate product to an end (instruct the computer what it needs to do) and another is YOUR direct output to some other human being, which is the end game in human-to-human communication.

Depending on the criticism at the time, they were probably wrong at the time and are correct now. There were always trolls and bad people but at least there were no mega-corp playing with people's minds.

Home can be sure the LLM is modifying just the prose style? Moreover, prose style is one of signal that convey information about what you are trying to transmit (unlike code, which is totally debatable if it should have meaning on its own).

You make errors and weird constructiona like we all non-native do and maybe eventually learn a bit more of English in the process. Or not. English dominance as the world's... lingua franca (ahem) deserves to have it bastardized ;)

Well, reputation is made by many dimensions. Writing takes like the UBI one is definitely a signal to take into account.

Mostly just the bash builtins have (had) this problem.

I think you didn't fully understand their post.