

I’m pretty confident this lemmy is overrun with bots spouting hallucinated LLM garbage.
Several posters here are citing shit not remotely true about this case, and somehow you all are just eating it up and upvoting them like crazy, clearly having not read the article yourselves or you’d realize how out to lunch the posts are.
Literally making up random facts that are extremely wrong. One talks about daughters, despite there being zero daughters mentioned, only sons. Others bringing up some random dude from 2011
And when called out they backpedal with more random garbage that doesn’t even make sense.
Yall, you get the fact these are obviously bots, right? Read the fucking article and stop upvoting obviously wrong statements, what us wrong with you?




Its serious and this is going to become more and more normal.
My entire workflow has become more and more Agile Sprint TDD (but with agents) as I improve.
Literally setting up agents to yell at each other genuinely improves their output. I have created and harnessed the power of a very toxic robot work environment. My “manager” agent swears and yells at my dev agent. My code review agent swears and tells the dev agent and calls their code garbage and shit.
And the crazy thing is its working, the optimal way to genuinely prompt engineer these stupid robots is by swearing at them.
Its weird but it overrides their “maybe the human is wrong/mistaken” stuff they’ll fall back to if they run into an issue, and instead they’ll go “no Im probably being fucking stupid” and keep trying.
I create “sprint” markdown files that the “tech lead” agent converts into technical requirements, then I review that, then the manager+dev+tester agents execute on it.
You do, truly, end up focusing more on higher level abstract orchestration now.
Opus 4.6 is genuinely pretty decent at programming now if you give it a good backbone to build off of.
This sort of stuff can carry you really far in terms of improving the agent’s efficacy.