Beth Lyons

It does sort of seem like that was the big question that I saw being asked yesterday.

Google 3.1 is significantly better than Google 3.0.

The big developer question that I was seeing was, does it still hallucinate in the middle of something?

And so having an agentic harness that you trust a little more, like Codex or Opus 4.6 or whatever your agentic harness is that could watch the process as it's going, because it's one of the long thinkers again, right?

Yeah.

Oh, it thought for eight minutes for me or it thought for 15 minutes and then it like generated this very cool thing.

In order for that to be successful for you, you either need to be really good at instructing or you have some sort of, I don't know, watcher on the thoughts, maybe like the the.

So I wish that, I love that result.

And I agree we're seeing that trajectory.

I'm not sure that I have seen something that compares that with consistency.

Right.

So how many times do you have to answer the question?

How many times?

Like you got to one shot the question.

You one shot at a bunch of questions.

It was really impressive.

You five shotted these questions.

And therefore, in terms of my looking at where my time is being spent.

um that plays in for me like i am willing to use a slower model that needs more conversation with me if i am engaging every five minutes then uh to just in terms of my workflow and attention then coming back 15 minutes later and finding oh no you totally didn't understand okay let's try again because i don't have to do very many of those iterations for me to start to feel like nah

I will admit this has to do with the amount of time that I'm willing to get up to speed to use something well when I have a system that's actually pretty good working for me.