[delusional]

For your context, I'm an AI hater, so understand my assumptions as such.

> The obvious best solution is to have your agent write release notes for your agent in the future to have context. No more tedious writing or reading, but also no missing context.

Why is more AI the "obvious" best solution here? If nobody wants to read your release notes, then why write them? And if they're going to slim them down with their AI anyway, then why not leave them terse?

It sounds like you're just handwaving at a problem and saying "that's where the AI would go" when really that problem is much better solved without AI if you put a little more thought into it.

[yoz-y]

For release notes in particular, I think AI can have value. This is because more than a summary, release notes are a translation from code and more or less accurate summaries into prose.

AI is good at translation, and in this case it can have all the required context.

Plus it can be costly (time and tokens) to both “prompt it yourself” or read the code and all commit logs.

[theshrike79]

If your process always goes PR -> main and the PR descriptions + commit messages are properly formatted, generating release notes shouldn't be much more than condensing those into a structured list with subheadings.

This is something LLMs are excellent at.

[antonvs]

What better solution do you have in mind? This scenario is AI being used as a tool to eliminate toil. It’s not replacing human creativity, or anything like that.

If you have a problem with that, then you should also have a problem with computers in general.

But maybe you do have a problem with computers - after all, they regularly eliminate jobs, for example. In that case, AI is only special in its potentially greater effectiveness at doing what computers have always been used to do.

But most of us use computers in various ways even if we have qualms about such things. In practice, the same already applies to AI, and likely will for you too, in future.

[bandrami]

It's not eliminating toil, it's externalizing it from the writer to the reader.

If writing something is too tedious for you, at least respect my time as the reader enough to just give me the prompt you used rather than the output.

[specvsimpl]

In a lot of my AI assisted writing, the prompt is an order of magnitude larger than the output.

Prompt: here are 5 websites, 3 articles I wrote, 7 semi-relevant markdown notes, the invitation for the lecture I'm giving, a description of the intended audience, and my personal plan and outline.

Output: draft of a lecture

And then the review, the iteration, feedback loops.

The result is thoroughly a collaboration between me and AI. I am confident that this is getting me past writer blocks, and is helping me build better arcs in my writing and lectures.

The result is also thoroughly what I want to say. If I'm unhappy with parts, then I add more input material, iterate further.

I assure you that I spend hours preparing a 10_min pitch. With AI.

(This comment was produced without AI.)

[bandrami]

Great example. Just give me the links you would give to the LLM. I also have an LLM and can use it if I want to, or I can read the links and notes. But I have zero interest in reading or hearing a lecture that you yourself find too tedious to write.

[aeon_ai]

Performative nonsense.

You have less interest in sifting through multiple articles and wiki pages sent to you by a stranger with a prompt than the one paragraph same stranger selected as their curated point.

And pretending like you’d act otherwise is precisely the kind of “anti ai virtue signaling” that serves as a negative mind virus.

AI is full of hype, but the delusion and head in sand reactions are worse by a mile

[bigstrat2003]

> And pretending like you’d act otherwise

No pretending here. I don't ever ask an LLM for a summary of something which I then send to people, because I have more respect for my co-workers than that. Nor do I want their (almost certainly inaccurate) LLM summary. It's the 2020s equivalent of "let me Google that for you": I can ask the bag of words to weigh in myself; if I'm asking a person it's because I want that person's thoughts.

[bandrami]

Then let him curate it as his central point. If he finds even that too tedious to do, I absolutely have no interest in reading the output of a program he fed the context to (particularly since I also have access to that program)

[jimbokun]

Because it’s not totally clear from your comment: what part are you contributing in this process?

[antonvs]

The original comment was saying that the AI would be both the writer now and the reader, in future. That's how the toil is eliminated. Instead of reading or searching through a series of release notes, you can just ask questions about what you're specifically looking for.

> If writing something is too tedious for you, at least respect my time as the reader

"If comprehending something is too tedious for you..."

Seriously, don't jump to indignant rhetoric before you're sure you've understood the discussion.

[bandrami]

What's the point of the AI writer in that use case? Just send your prompt to my AI. And for that matter since prompting is in plain English, why not just send your prompt directly to me, and I'll choose to prettify it through an AI or not as I prefer.

[antonvs]

The point is that it summarizes the context. It’s an important optimization, because context and tokens are both limited resources. I do something similar all the time when working with coding models. You’ve done a bunch of work, ask it to summarize it to the AGENTS.md file.

The more fully automated agents rely heavily on this approach internally. The best argument against it is that good harnesses will do something like this automatically, so you don’t need to explicitly do it.

Sending you the prompt wouldn’t help at all, because you’d have to reconstruct the context at the time the notes were written. Even just going back in version control history isn’t necessarily enough, if the features were developed with the help of an agent.

[bandrami]

But I also have access to an AI that can summarize content. So why not just send me the content and the prompt you used? Or just the content, so I can summarize it however I want?

[funnybeam]

In this scenario the ai _writer _ is redundant.

You might as well publish the prompt you were going to give to the writer and have the ai reader consume that directly.

Assuming you think any of this is a good idea of course. Personally I wouldn’t trust ai to interpret release notes for anything that i cared about

[antonvs]

I responded to a similar point here: https://news.ycombinator.com/item?id=47584324

The original commenter was essentially describing something similar to what good agent harnesses already rely heavily on.

[watwut]

Obvious better solution is to either a.) not write those release notes b.) try to figure out release notes format and process that leads to useful release notes. Once it is useful, you can decide to automate it or not - and measure whether automation is still achieving the goal.

What OP did was "we lacked communication, then created ineffective process that achieved nothing, so we automated the ineffective process and pay third party for doing it".

If you pay tokens for release notes that nobody reads, they you may just ... not pay tokens.

[necovek]

To me, the value I would look to extract feom LLMs is turn the code changes into user-readable, concise release notes.

If you are coding with the help of LLMs, then release notes are your human-crafted prompt.

Basically, the intent is given as a decision somewhere, and that is human driven.

[dahfizz]

This is kind of a fundamental issue with release notes. They are broadcasting lots of information, and only a small amount of information is relevant to any particular user (at least in my experience).

If I had a technically capable human assistant, I would have them filter through release notes from a vendor and only give me the relevant information for APIs I use. Having them take care of the boring, menial task so I can focus on more important things seems like a no brainer. So it seems reasonable to me to have an AI do that for me as well.

[bandrami]

I read a lot of release notes in my job and the idea that that is some kind of noticeable time sink that needs to be streamlined is bizarre to me. Just read the notes.

[necovek]

If your assistant is technical enough to know which parts apply to you and which do not, they likely don't need you to do the rest of the job either.

An LLM could do this by looking over the full codebase and release notes and do a shorter summary, bit probably at the cost of many tokens today.

[jimbokun]

Or you could Ctrl-F.