The PMs validate it, why do you think they don't read over it to make sure it fits what they want? You might say "well they're lazy, look why they didn't write enough detail to start off with" but for lots of people, reviewing something to make sure it's close to what they want and then tweaking it is much easier than writing it from scratch.

It's the equivalent of writer's block and is why a common advice given to writers is to put anything they can onto the page then edit it later.

▲

majormajor 3 hours ago | parent | next [-]

> The PMs validate it, why do you think they don't read over it to make sure it fits what they want?

The PM has historically often not had a detailed enough mental model of the implementation to spot the hard parts in advance or a detailed enough mental model of the customer desires to know if it's gonna be the right thing or not.

Those are the things that killed waterfall.

You can use LLM tools to help you improve both those areas. Synthesizing large amounts of text and looking for inconsistencies.

But the 80th-percentile-or-lower person who was already not working hard to try to get ahead of those things still isn't going to work any harder than the next person and so won't gain much of a real edge.

	▲	Avicebron 3 hours ago \| parent \| next [-]
		I'm glad you mentioned it and TFA briefly mentioned waterfall. The second graph shown in the article with documentation overlapping the dev cycle, it's like the worse of both agile and waterfall. It's supposedly real-time waterfall. Normally waterfall works where the scope is extremely-well defined and articulated in design plans. Which shortens dev time because prior to AI code was mostly deterministic. Here we have to do waterfall level of documentation while iterating on a non-deterministic solution (code gen) to non-deterministic requirements (per usual). It's bonkers. I still think the technology is cool though. And to answer the questioner.. Have you worked with a PM? Most of the ones I've worked with try to be simultaneously in charge yet not responsible for anything. Validating something implies skill and responsibility.
	▲	satvikpendem 2 hours ago \| parent \| prev [-]
		Then they're just bad PMs and don't deserve to have the job. That can be said in any profession, devs or lawyers or doctors who blindly accept LLM output without review are bad employees.

▲

zxornand 3 hours ago | parent | prev | next [-]

I think validating a fully generated novel of a ticket, is much harder than thinking through the problem in the first place and creating your own ticket.

We see it with code too right? It’s harder to review code than to write it.

On top of that the LLM can work so fast that the amount of things that need validating grows!

This is where humans get lazy and the problems come in IMO. Whether its a PM not validating their ticket, or a dev doing a bad code review.

Add on to that that the incentives currently are to move fast and trust the AI.

It becomes clear to me that a lot of that review work either won’t be done at all, or won’t be nearly thorough enough.

▲

satvikpendem 2 hours ago | parent | next [-]

The tickets are not "novel"-length, they are about a few bulleted lists of the sections I mentioned above. In that case it is indeed way easier to review that a ticket only saying "do X with Y data."

Reviewing code is harder than reviewing text because code does something and has interdependencies and therefore must be correct in its function, do not mix the two. This is like saying an editor reviewing an article or novel is harder than actually writing the novel which is blatantly incorrect.

	▲	zxornand an hour ago \| parent [-]
		Most real tickets are more complicated than “Do x with Y data” and also have many interdependencies throughout the business

▲

paulhebert 2 hours ago | parent | prev [-]

I agree. I hate getting tickets like this because they’ve often gone down the wrong path and I have to work backwards to understand the actual problem and the right way to solve it

▲

mrbombastic 2 hours ago | parent | prev | next [-]

just this week i pushed back on some requirements in a very detailed product spec I was implementing to speed up time to ship. The pm had no idea what I was talking about because the requirements were invented by an LLM. This is not a bad PM, discipline doesn't scale.

▲

BugsJustFindMe 4 hours ago | parent | prev [-]

> The PMs validate it, why do you think they don't read over it to make sure it fits what they want?

Hahahahahaha. Sorry, I couldn't help myself; this reads like satire. The answer is "real life experience says otherwise".

▲

ethin 2 hours ago | parent [-]

Yeah I was so tempted to ask if this person has ever actually met a project/product manager...

▲

satvikpendem 2 hours ago | parent [-]

Maybe you both just have bad PMs, because just like good devs they should also be reviewing their work. My point was that it is more likely for PMs to review and edit a generated ticket than to have to write it all themselves which they often won't do.

	▲	BugsJustFindMe 2 minutes ago \| parent [-]
		> My point was that it is more likely for PMs to You keep making claims like this. I feel compelled to point out to you that this is a completely unsustainable, unsupportable, unsubstantiable claim. You have met ~0% of PMs, and of the ones you've met maybe you've experienced a non-zero percentage of their work, but statistically that's also very unlikely. If you think you can say what PMs do, what PMs are likely to do, what PMs do on average, then, I'm sorry, but you are not even thinking like an engineer.