Hacker News Reader

Comment by anthuswilliams | Hacker News Reader

One interesting quirk of the AI-written READMEs these days is how they can include every detail on how it works, thoroughly document every optional flag, known limitation, experimental result, and still not communicate the essence of the project and the problem it solves.

I have read through the project and I still don't understand what this thing is for and why it is to be preferred over the harness's native memory management tools.

View on HN

Yeah, I've started dialing back my use of AI for READMEs because of this.

My previous rule was that I never use AI for writing that expresses my own opinions or tries to be convincing (anything on my blog for example) but I'll let it do technical documentation.

The top of a README is about convincing and explaining why I built something though, which means it should fit my no-AI policy after all.

Just prompt the AI to keep README concise and to the point, and to remove any implementation details that don't belong in README-style documents. I regularly run such debloating/decluttering prompts on my docs.

I don't understand people leveling criticisms at the output of AI, when that is exactly how you program them. Have people all forgotten the "prompt engineer" phase of our roles?

Give them 2 positive examples. A list of things to do, a list of things not to do and you have them giving you the exact output you want.

"Write a readme make no misteaks" is not deft usage.

The AI language really stands out, too. "What is automatic and what depends on the agent". A human might write, "jevmen watches your coding session with Claude Code or Codex and picks just the right moment to remember important things that you decided along the way. There are some differences in how jevmem works, depending on which coding harness you are using. The table below summarizes these differences:"

I don't know why the models were generally trained to be so brief, but it's definitely not the way anyone I know actually writes. A second pass is always a good idea to clean this stuff up. And, thankfully, the models are all pretty good at that.

The big tell for me is assuming the reader has context straight out the gate. "What is automatic and what depends on the agent" assumes the reader, like the LLM at the time it wrote that sentence, has all of this pre-context available. That sentence makes more sense as an h3 header further down in some detailed list where the human has all of the knowledge of how the system works. Whereas a human obviously does not, so they lead with the important context of why you give a shit

My pet theory is that while the pretraining -> RL pipeline achieves very impressive results, it does not reward clarity of thought or elegance. It's not obvious whether it even should for most tasks, but it does grind on me as a human who needs elegance in order to keep everything under control. You give astra/codex many tasks, it retires them all more efficiently than I could by hand. But you look under the hood and every bugfix is another codepath, it just hammers away at things with admirable persistence and vigor until the tests pass. Similarly in discussions and docs, I've noticed many LLMs like to "beat around the bush."

it does not reward clarity of thought or elegance.

Well duh. RL can only train behaviors that can be defined. Clarity and elegance are damn subjective.

Also, I doubt we'll ever get AI to understand what clarity is to a human. They have such enormous contexts that what's clear to them is not clear to us.

Subjective doesn't mean you can't define it. RL works well for human preference and any other subjective goal as long as it's defined. In fact Claude used to be trained for human likeness, reading between the lines, character, languages, and understanding the intent. Claude 3 was outstanding in that. It was their entire marketing shtick. Then they neglected it starting with Sonnet 3.5, ignored it in favor of code since Claude 4.0, and new models completely lost their ability to write and understand humans. Code pays better.

I once told the agent explicitly not to write like it's trying to impersonate Hemingway and it started writing like a normal human being. It's surprising how a writing style that was once revolutionary is now a hallmark of sloppyness.

Maybe give it a try next time you write a readme with agents. That and giving it an example of good README in real world repos can increase dramatically the likelihood of synthesizing a serviceable README.

It's a function of scarcity. Generation (or "writing" as it used to be known back in the day) is now cheap, so judgement and taste are the new bottleneck and therefore the difference between slop and effort.

I don't recall Hemingway ever using semicolons or em-dashes.

Next time you read I suggest focusing less on punctuation and more on style of writing, because it's not about which syntactic markers you use, but which words you choose and how you use them, emdashes notwithsanding.

Hemingway did not write like a LinkedIn influencer, if that's what you mean.

He wrote in short bursts. Sentences that connect but barely. Crude, honest. It's not a style you want to use for flow. It's a style you want to use to impress.

AI readme should be a starting point. I typically remove at least 50% of the details (without any particular skill use, it goes into extremes like "x clears the edit" and writes a related wall of text in the middle of the important explanation).

This is quite easily promptable. Tricks like these do well: https://news.ycombinator.com/item?id=49065956

It’s funny to me because pre-AI it’s something I something I saw all the time managing interns and junior software engineers when I’d start trying to tech them about writing design docs. You can explain the process to them and give them a million examples of what good looks like, but for a lot of them the first few docs they write will just be this weird combo of way too much information and very little of it being useful.

My belief has always been that they see the document as more like a test that’s a single task and not just one piece in a larger process and so they treat it like a test where there’s a right answer. They know they don’t really understand the question being asked though so they default to a mindset of, “Well if I just put everything in there some of it has to contain the correct answer” so you end up with this document that’s full of “what”s and “how”s, but completely void of “why”s.

You’ll also often see them fill up space answering easy questions that match the structure of things that are in other documents instead of focusing on the actual hard problems in the design because the hard problems are often unique and their answers may not fit the existing patterns in the examples. There isn’t the instinct to go, “Yeah, none of these example documents talk about the servers were going to deploy it on, but this has to be deployed in an EU cluster because of GDPR laws so I need to add that” because they’re mostly just pattern matching at first.

Usually once they’ve experienced the whole process first hand it starts to click because they start to understand where a design document fits into the larger process so they get a feel for what information matters and what doesn’t.

I think when people just tell an agent to create a README you have the same problem because both the human and the agent see it as just a checkbox type task. The agent sees it as an isolated task snd has no fucking idea how the README is going to be used and the human isn’t giving them that context so they just spit out a bunch of stuff that’s factual and fits the patterns it knows, but is fairly useless.

Fair point on the README. Short version of what it’s for:

Coding agents forget project decisions across sessions. You say “use Postgres, not SQLite” on Tuesday; Thursday a fresh chat invents SQLite again. jevmem watches each turn (Claude Code hooks; Cursor/Codex via agent/MCP), asks Jev a few typed save/skip questions, and appends keepers to JEVMEM.md in the repo. Change your mind later and the old line is marked superseded, not deleted. Next session those lines get injected back into context.

Vs Claude Code’s native memory: native is Claude deciding what to write into its own auto-memory / MEMORY.md under the local project store. That’s free and local. jevmem is different on purpose: the file lives in the repo (git-friendly, shareable), save/skip is a small typed gate rather than free-form “Claude, remember this,” and superseding is first-class. Tradeoff is real: scrubbed turn text goes to TypeSafe’s Jev API (and optionally an LLM to write the line), and full auto-capture is Claude Code only today.

Not claiming it’s always better than native. Prefer it when you want a repo-owned decision log that survives sessions without you prompting “remember that.” Prefer native (or nothing) when you want zero third-party traffic.

Fair. Short version: Claude Code (and friends) already keep session/auto memory, but it lives in the harness. jevmem’s job is a JEVMEM.md in the repo so decisions travel with the project across sessions and tools. After each turn, Jev scores whether anything is worth keeping (decision, constraint, bug, change of mind). Capture is fully automatic in Claude Code today; Cursor/Codex need the agent/MCP path (or jevmem watch for Codex). If the README buried the "why", that’s on me.

Reply on news.ycombinator.com