News for hackers. Stuff that matters.
Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by spiderice on Thursday November 19, 2026 @05:20PM (#50567295)
> but setting it up to do that work correctly and safely still takes skill

For now. Not sure why you think that would last though. Obviously the big labs are going to make it easy to use AI both safely and correctly. It's already significantly easier to do that today than a year ago.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by dotancohen on Thursday November 19, 2026 @05:49PM (#50567646)
I completely disagree. The AI tools I've used from the big shops are happy to code visible features, but need real restraint to keep things in order.

I no longer really check the code, but I won't let any of them touch the database schemas. I modify the schema, the machine codes around my database. Same policy with APIs, even private ones.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by equinumerous on Thursday November 19, 2026 @05:53PM (#50567698)
> but need real restraint to keep things in order.

I second this. Even OpenAI's flagship models... the code I write by hand has much less entropy and is easier to follow than the equivalent AI-generated code. I think part of the software engineering skill now is knowing which pieces you can delegate to AI and which still need human input. I know many people who just YOLO it all and have AI do everything... but, this can hardly make for a stable system in my opinion...

And, I'll be happy to be proven wrong, because it will mean a significant amount of work is off of my shoulders. But I think we aren't quite there yet in terms of having AI code that lowers the complexity instead of raising it in a codebase.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by bentobean on Friday November 20, 2026 @06:04AM (#50573019)
I hear you, and I agree with you. But the response to this by leaders at my company would be:

> Why are you looking at the code? Complexity? What do you care? Let the agent handle that.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by dotancohen on Friday November 20, 2026 @02:25PM (#50580457)
Those are good questions, why are you afraid of them? Answer them and move on. You do have a convincing answer, right?
Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by equinumerous on Friday November 20, 2026 @05:57PM (#50583547)
> Why are you looking at the code? Complexity? What do you care? Let the agent handle that.

Because when I don't look at the code, bad things happen. Outages, customer data is deleted, security issues.

I can hear the reply: "Why not let agents review the code?" - that's true, but at some point my boss is going to hold me responsible, and I'm going to have to answer for it. Both ethically and practically speaking I have to make the responsible engineering decision and actually own my actions.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by spiderice on Friday November 20, 2026 @04:55PM (#50582833)
Check back in a year. Time is going to prove you wrong.
Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by geraneum on Thursday November 19, 2026 @06:16PM (#50567947)
> Not sure why you think that would last though.

The failure modes of the LLM are still the same. Nothing has fundamentally changed, despite the UI and the harness showing significant improvements and outcomes.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by wolttam on Friday November 20, 2026 @09:25AM (#50575071)
I almost never hit the failure modes of LLMs anymore, they have been getting much more reliable year over year.

More and more it would appear the failure modes are a training data issue

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by geraneum on Friday November 20, 2026 @10:31AM (#50576175)
> I almost never hit the failure modes of LLMs anymore

Of course you do. Just because you don’t see the LLM trying the ls command for the billionth time with the wrong arguments, just to be corrected by the harness, doesn’t mean it doesn’t happen. Of course I use the ls cli as an example. Could be any task. That’s what I mentioned about the harness and that’s why they shine in the fields with hard verification mechanisms and feedback loops.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by wolttam on Friday November 20, 2026 @01:17PM (#50579324)
I actually use my own harness that doesn't attempt to fix broke tool calls. Yes models are not perfect and they do make mistakes, but my experience has been that reliability has been trending only upward. I really can't remember the last time I saw a tool call loop.

(this has been my experience since ~DSv4 from April)

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by geraneum on Friday November 20, 2026 @02:07PM (#50580144)
> I actually use my own harness that doesn't attempt to fix broke tool calls.

It’s not the harness that attempts to fix the broken tool calls. It’s the LLM.

> last time I saw a tool call loop

We are not talking about tool call loops

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by wolttam on Friday November 20, 2026 @04:11PM (#50582166)
> It’s not the harness that attempts to fix the broken tool calls. It’s the LLM.

Then what did "Just to be corrected by the harness" mean?

> last time I saw a tool call loop

Reasoning loops, output loops, etc, I just don't tend to see them with the models I use.

All I'm saying is that I find LLMs to have been consistently getting more reliable, to the point that their failure modes don't really stand out.

Re:AI Came for the Coders. Understanding Why Tells Us Who's ... by docshock on Friday November 20, 2026 @05:53AM (#50572916)
Your trust in the big labs may be misplaced. What do they rent you? A black box that cannot be inspected.

If you actually start looking inspecting what the boxes do, it is a scary place. The Chinese models are open source open weights and are trained on lies. This much can be proven. But the frontier labs have made it impossible to determine the provenance of their models. They have been fed with copyrighted works, but good luck proving that your copyrighted work lives in their weights.

In short, the frontier labs are operating opaquely, and that's very good reason not to trust them.