News for hackers. Stuff that matters.
Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @01:34PM (#50564146)
Take this as genuine advice, not criticism: The fact that you felt the need to “characterize” the jank and verbally describe it is evidence of your mistake. The only way for these new development models to function is to create a tight machine-only validation loop. Every aspect of an LLM-generated text editor must be drivable fully by the LLM itself so that it can independently observe the problems and fix them.

LLMs won’t always guide you to do this correctly so you need to understand how important it is from the start and always enforce it.

Re:Anthropic hits $2T in Nasdaq debut by groestl on Thursday November 19, 2026 @01:42PM (#50564285)
> always enforce it.

Here be lions, since these things tend to lie to you or themselves when skipping the enforcement part.

Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @09:34PM (#50569461)
Just slap another agent on top to fix it.
Re:Anthropic hits $2T in Nasdaq debut by qlte on Thursday November 19, 2026 @01:42PM (#50564299)
I'm not seeing any indication that OP didn't do that. The jank they're describing sounds exactly like something that could slip past the harness' validation loop (weird intermittent graphical anomalies).
Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @07:44PM (#50568692)
Then the equivalence I am talking about is imperfect in OP’s case. LLMs should have control surfaces and sensor inputs isomorphic to those used by humans. If the human can notice the jank and the bot cannot, that is a thing to fix.
Re:Anthropic hits $2T in Nasdaq debut by the_real_cher on Thursday November 19, 2026 @01:43PM (#50564300)
I'm not sure you're correct.

If the software was capable of creating high complexity software I, or anyone, should be able to replace and build anything I want with just some prompts and guidance.

Anyone who has worked with LLM heavily knows this is far from the truth.

Re:Anthropic hits $2T in Nasdaq debut by dboreham on Thursday November 19, 2026 @01:58PM (#50564559)
What thing that you want have you failed to build?
Re:Anthropic hits $2T in Nasdaq debut by the_real_cher on Thursday November 19, 2026 @03:43PM (#50566089)
A new operating system?
Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @10:49PM (#50569912)
Post your failure then.
Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @10:53PM (#50569937)

  > I should be able to […] build anything I want with just some prompts and guidance.
…Yes? You can. That’s why some people are excited. The fact that agents can do a thing does not mean that you don’t (currently) need skill and taste to guide it in the right direction. No one said it was a magic button. Just a new form of cognition. And god knows I don’t expect all the human cognition I encounter in my life to be the image of perfection…
Re:Anthropic hits $2T in Nasdaq debut by asdfman123 on Thursday November 19, 2026 @01:47PM (#50564365)
I find LLMs produce very good results if you just prompt it into good software engineering practices. Write thorough unit tests, minimize diff noise, try to re-evaluate all work to see if it can be done more elegantly and simply. Then you can run an adversarial review agent to catch any bugs it missed.

Same goes for AI slop comments. I can just prompt AI into more or less writing like me.

Re:Anthropic hits $2T in Nasdaq debut by titzer on Thursday November 19, 2026 @01:48PM (#50564379)
Yeah, this is really important. Having a tight test loop is already great for humans, but doubly-so for agents. A clunky manual process sucks for humans and agents alike.
Re:Anthropic hits $2T in Nasdaq debut by jaykru on Thursday November 19, 2026 @01:57PM (#50564546)
I appreciate the friendly tone :-) and I mean this not as a jab: I think maybe you missed the point of my comment above, which wasn't that one can't build functional software with LLMs, but rather that it requires the diligent involvement of a technical worker.

> Barring an architectural paradigm shift we will still need people with strong engineering and design instincts, and even more importantly the ability to write reference code and formal specifications codifying desired behaviors.

The people building those specifications and the tight validation loops you describe are the technical software workers of tomorrow.

Re:Anthropic hits $2T in Nasdaq debut by PhilipRoman on Thursday November 19, 2026 @02:19PM (#50564863)
I generally agree with your point, however you can also say "Hey Claude, I want to vibe code XYZ, set up an AI friendly automation environment". And of course it doesn't have to be you saying that, it could be a N+1 level agent, who loaded his /ai-project-management-best-practices skill.
Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @07:59PM (#50568811)
Right. Draw the line out where it’s pointing right now and there only so many turtles to make up “all the way down”.
Re:Anthropic hits $2T in Nasdaq debut by semiquaver on Thursday November 19, 2026 @07:45PM (#50568703)
With absolute, genuine sincerity: I hope with all my heart and soul that you are correct.

Best, friend.