Live data from Hacker News

Cognitive Debt: When Velocity Exceeds Comprehension

rockoder.com

231–234 of 234 posts

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#231

Earlier quoted context omitted.

The problem isn't giving MORE context to an agent, it's giving the right context These things are built for pattern matching, and if you keep their context focused on one pattern, they'll perform much better You want to avoid dumping in a bunch of data (like a year's worth of git logs) and telling it to sort out what's relevant itself Better to have pre-processing steps, that find (and maybe summarize) what's relevan…

"You want to avoid dumping in a bunch of data (like a year's worth of git logs) and telling it to sort out what's relevant itself" So instead you give it a years worth of changelog.md? "Better to have pre-processing steps, that find (and maybe summarize) what's relevant, then only bring that into context" So, not a list of commits that touched the relevant files or are associated with relevant issues? That kind of "p…

Hey you can try it if you like. That's one of the beauties of the current moment, nobody REALLY knows what works best, just a whole lot of people trying stuff

And no, I wouldn't ever give it a year of changelog.md. I give it a short description of the current functionality, and a well-trimmed list of 'lessons-learned' (specific pitfalls/traps from previous work, so the AI doesn't have to repeat them)

If you think git logs are a good way to give context, try it and and see how it works! My instinct's that it won't work as well as a short readme, but I could be wrong. It's so easy to prototype these days, no reason to not give it a shot

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#232

Earlier quoted context omitted.

exactly, as a manager and a sometimes a developer, "vibe-coding" has been looking more and more as my day job (in a good way, it's good to not have to do all the dirty work for your pet projects) and it's all about having the same discipline in term of: * thinking about the big picture * knowing how you can verify that the code match the big picture. In both case, somtimes you are happily surprised, sometimes you dis…

Engineering is not "dirty work." Management is not "engineering."

It's not what I've written.

To clarify, by "dirty work on my pet project" , I meant ,spending times to fix some compilation issues that after 2 hours you told yourself "damnit, I forgot this!" , or when you want to adapt your old python project from python2 to python3.

And I didn't even talked about managment itself.

But , thinking about the big picture, telling claude code to not use this but that. To not overengineer etc. is engineering in my book, and what I've been been doing for the last 8 years at least with more junior engineers.

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#233

Earlier quoted context omitted.

"You want to avoid dumping in a bunch of data (like a year's worth of git logs) and telling it to sort out what's relevant itself" So instead you give it a years worth of changelog.md? "Better to have pre-processing steps, that find (and maybe summarize) what's relevant, then only bring that into context" So, not a list of commits that touched the relevant files or are associated with relevant issues? That kind of "p…

Hey you can try it if you like. That's one of the beauties of the current moment, nobody REALLY knows what works best, just a whole lot of people trying stuff And no, I wouldn't ever give it a year of changelog.md. I give it a short description of the current functionality, and a well-trimmed list of 'lessons-learned' (specific pitfalls/traps from previous work, so the AI doesn't have to repeat them) If you think git…

"a short description of the current functionality, and a well-trimmed list of 'lessons-learned'"

Where does that come from?

"And no, I wouldn't ever give it a year of changelog.md."

No, instead you'll "[run] your git history through a cheap model". Except it's "overkill and error prone". So you're writing it up yourself? You didn't do the work, how do you know what the pitfalls and traps are?

Re: Cognitive Debt: When Velocity Exceeds Comprehension

#234
One idea that comes my mind - create a note with full context of what went through during the development and then ask LLM to use that note and actual code to quiz yourself so that you can understand if you have got enough grasp. While doing this exercise, it will add some friction and build some memory of what you did. You can also understand what additional documentation you would need to be able to get grasp of what you did, when you read code again in future.
Post reply on HN