This is becoming more and more true.
1,340 karma · joined July 25, 2022
This is becoming more and more true.
And then on top of that you need another agent to manage merging all of the subagent code together?
But imo the real reason is that they enjoy alcohol and don't enjoy gambling.
You're making a bad faith argument that all gamblers are slaves to the casino. The overwhelming majority of gamblers do not have a compulsion.
And, as a percentage of participants, alcohol is significantly more likely vs gambling to result in addiction, and far more likely to kill someone.
Freedom includes being free to self regulate and to make mistakes.
1. Review what it writes as it writes it
2. Give it a smaller, more focused, scope to make changes
Or, keep vibing but then don't get mad about it.
Knowing your zip code isn't a skill though.
I don't know my ATM pin. Does that make me an idiot? Turns out I just don't need to know it.
So now I do it regularly.
The words we have are fine.
We just need to assign liability by ownership/initiation: if your "agent" destroys something, even though you didn't tell it to (because it had "agency"), you should be liable for the damages.
My counter point was that everything we do doesn't have to be motivated by efficiency gains. Sports, golf especially, isn't trying to cram the most people possible into a small space.
By your own logic, we should replace soccer fields with kicking a ball into a net.
It sounds like you're arguing against modularizing which is an unusual stance. Especially for a million line codebase.
This is what we've been doing for years before LLMs. Hiring a ton of devs to spit out code, which became another's burden. It just took longer and cost more.
I think the first one is the whole story anyway.
If we don't want idiots to do idiotic things we probably shouldn't make it possible/legal in the first place. But the corruption and malfeasance goes way beyond Trump so here we are.
If you implement AI code review suggestions then you're using AI code, just the hard way.
Also I don't see why your clients would be ok with having AI review and influence your code. Seems hypocritical, or like you're trying to cheat them.
LLMs are great at this. I'd be very surprised if it wasn't possible to improve the actionable notes.
Most human-made doctor notes I've seen have not been comprehensive, anyway, and the doctor has had to spend a good chunk of a rushed appointment scribbling notes rather than interacting with the patient.
You don't blindly follow it, and you also don't order a DNA test of the person that made it. You look at the output to include supporting evidence.
And you have a process for appeals.
That's distasteful.