When I work with Claude to plan a feature and then review Claude's implementation, I don't understand the feature as well those I developed without AI assistance. I don't recall details of the feature's behavior as well, even days later. I suspect that this is not surprising to anyone who has studied pedagogy. I've been working on applying some exercises during code review (including self-review of my own AI-assisted code) to improve comprehension and recall (https://bridgekeeper.io/). If this problem resonates with you, I would like to talk.

This looks pretty cool, but doesn't it reduce velocity? If CTOs want more code shipped faster, this might slow things down

I'm working on a possibly-quixotic tool to mitigate the "cognitive debt" from AI-assisted development. Not everybody agrees that this is a problem. Maybe some teams that are only writing specs and reviewing plans still understand their products adequately. If you have an opinion either way, I'd appreciate hearing from you.

I'm working on something similar; are you interested in seeing whether there are opportunities to collaborate?

Hey man - yeah I’m down to chat! My email is in my bio so just reach out there and we can chat

I'm working on a tool for mitigating the cognitive debt from AI-assisted development. Pedagogical research provides some techniques we can use in code review to improve comprehension and recall. If this resonates with you, I'd appreciate hearing more about your experience with cognitive debt.

I'm working on a tool for mitigating the cognitive debt from AI-assisted development. Even when I review Claude's diffs line-by-line, I don't understand them as well as code I wrote myself, and I have difficultly recalling them days later.

Pedagogical research provides some techniques we can use in code review to improve comprehension and recall.

This doesn't resonate as a problem with everyone, but I'd like to hear from you either way.

Also, the tool talks like the Monty Python bridgekeeper, for whatever reason.

https://bridgekeeper.io/

If I read “load-bearing” or “blast radius” one more time…

Don’t forget about the “smoking gun”

The post’s title is mostly occluded by an image on mobile, so that bodes well.

> Farts for busy people who dont have time and also LLMs

30/100

> an app that tells you how potent your poo is, and rates it against other poos to see who has the worst poo

35/100

My start up is going to crush yours.

This is exhausting.

You sir are a tiredness engineer

Location: Philadelphia, PA

Remote: Yes or Hybrid in NYC

Willing to relocate: No

Technologies: Python, PyTorch, scikit-learn, pandas, Django, Flask, FastAPI, PostgreSQL, Swift, SwiftUI, HTMX, JavaScript, React, Terraform

Résumé/CV: https://docs.google.com/document/d/1MK6O_lsRz_x3gD6NFBkWPiHY... Email: gavinhackeling@gmail.com

I am a generalist software engineer, data scientist, and engineering manager with more than twelve years of experience at early-stage startups backed by Breakthrough Energy, Emerson Collective, Founders Fund, First Round Capital, GV, General Catalyst, and IA Ventures. I have built products and engineering teams from scratch and led them to seven-figure ARR at two SaaS companies. I am the author of the first and second editions of Mastering Machine Learning with scikit-learn, and the inventor of one patent.