cd /news/ai-tools/episode-531-shallow-feedback-and-my-… · home topics ai-tools article
[ARTICLE · art-136091] src=softskills.audio ↗ pub= topic=ai-tools verified=true sentiment=↓ negative

Episode 531: Shallow feedback and my coworker is a huge sloperator

The 531st episode of the Space Therapists podcast features a listener question from a consultant who struggles to gather feedback on shallow, uncoordinated work across roles including interim PM and advising SAP developers on coding agents, and a second question from a small-team engineer whose coworker submits overly verbose AI-generated pull requests with misleading docstrings, overly complicated functions, and failing tests that degrade production. The coworker's AI-assisted code is piling up in review, and the listener asks how to address it without commenting "ai slop" on 50% of the code.

by read1 min views2 publishedSep 21, 2026

In this episode, Dave and Jamison answer these questions:

Listener Jame ain’t no dance asks,!

Hey Space Therapists, I am a consultant that helps big companies to fix all kind of stuff. It’s ridiculous how many different hats I wear. One day I’m the interim PM, the other day I am telling SAP devs how to use a coding agent, next day I gather stakeholder requirements for a customer self service portal. I do all of these tasks on a fairly shallow level and all of that work is happening without much coordination from my company. I think I do a good, but it’s hard gathering feedback on my work, since no colleagues are involved and I can’t simply ask the customer without revealing insecurity. Send sophisticated tips and don’t make me quit. Cheers!

Can I tell a coworker to stop using Claude?

I work on a small team at a midsized company, and a coworker keeps dropping overly verbose pull requests that are full of AI jargon. These are increasingly hard to understand, and then when I ask for design intent clarification I often get sent a long document that is even harder to understand!

And the code sucks! misleading docstrings, overly complicated functions, and weird places where the AI has convinced them that something needs to be backwards.

And often times I end up having to fix failing tests (that my coworker probably didn’t run), or report back later that their changes have degraded something in prod or is causing a lot of logging noise.

I worry that I’m doing the same thing and just not noticing. Code is starting to pile up in review and I don’t want to be rude and comment “ai slop” on 50% of the code! What can i do?

── more in #ai-tools 4 stories · sorted by recency
github.com · · #ai-tools
Pipper
── more on @space therapists 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/episode-531-shallow-…] indexed:0 read:1min 2026-09-21 ·