This. Also I'm finding out that, after being blown away by agent mode lately, non-agent mode still kind of sucks across frontier models. Using GPT and Gemini in non-agent mode is asking for inaccurate information confidently presented as the truth. Turning on agent mode fixed a lot of that for me.

▲

IshKebab 3 hours ago | parent [-]

I think it's because of the lack of feedback. Humans also can't do much without feedback. E.g. I doubt most people could write 100 lines of code that works first time without even compiling it once.

▲

nswango 2 hours ago | parent [-]

Disagree. When tool limitations meant that this was the way people had to work, many people could do this.

It was much more inefficient, because it's easier to find bugs after compiling or running the code. But it is perfectly possible.

	▲	okwhateverdude an hour ago \| parent [-]
		Even more extreme than that, if you were working on a large code base where compiling it took forever, or you needed to rely on a very slow CI pipeline, it became very important to git gud and write shit that worked first time in order to deliver when promised. I'd argue if you've never had one of those moments where you sunk a bunch of time into some changes and it all compiled/worked flawlessly the first time, you're missing out.