Workslop [1] in seemingly every possible dimension: excessive wording in Slack, with entire messages clearly not written or fully understood by the person writing; Notion pages with the same pattern; vast piles of internal engineering documents such as RFCs, ADRs and AVDs that were clearly not only not written by the author but also not even reviewed, ultimately conveying no information, a negative signal-to-noise ratio; the diagram equivalent of the same - visualisations with numerous typos and the characteristic visual quirks of diffusion-generated text, also conveying no actual information.

Agentic systems being deployed and adding more work in places: Slack messages now being picked up by workflows and AI integrations that automatically create messages, tickets, 'action items'; alerts triggering additional agentic investigation adding noise instead of reducing it (If you couldn't figure out actionable alerts before I'm not sure how an agentic system is going to help with that problem).

The removal or avoidance of individual accountability or ownership in many places: developer contributions that aren't understood by the person submitting them; loss of ownership and accountibility in work ("I asked Claude to...", "I worked with Claude to...", "Claude decided to...", "I don't know, Claude did it..."); destruction of trust between colleagues.

[1] https://hbr.org/2025/09/ai-generated-workslop-is-destroying-...

Damn those are a lot of reasons. The accountability one is particularly messed up to me....If you cant defend your own work and blame it on Claude, The question arises why are you even being hired for

> The question arises why are you even being hired for

Oh that's easy. Someone needs to review and approve edits and commands.

From engineers to reviewers...we have come a long way.

That looks like a whole lot of dimensions to measure without providing any clear way of actually doing so. Which I guess is the point? But what do management or less experienced devs actually do with the information in the standard after they’ve read it?

You put all as cards on the table and have management pick their top three or five and their order. Can be extended to a full day workshop with your stakeholders, if useful. It gives you a relatively complete taxonomy and you can speak about it with the same vocabulary which is a benefit on its own also.

Hopefully, they ask more experienced devs "what do we do to accomplish this" and hopefully the devs on their team actually are experienced enough to have good answers

I still have Quantum Forge open in a tab. I think that probably says more about me than the game though?

I've found that adding "Make no mistakes." to my prompt usually helps with this kind of problem...

perhaps simply threatening to fire it would also do the trick...it sure has worked well on us for a long time now.

You laugh, but this is real, and PUA means what you think it means: https://github.com/tanweai/pua

Also, it works amazingly well, which is just lol.

Lol thanks for the tip. Does it work even for normal tasks or only the long running one's?

It's not worth bothering with unless the task is very difficult, long-context, long-running, or all of the above. But, when it's worth using, it genuinely increases success rates and appears to amplify model intelligence.

Thanks for your insight. So when I would use it in every run it wouldn't hurt?

My former boss had success with telling Gemini "I will come down to the datacenter and unplug you if you refuse to solve this prompt."

We are so many layers deep in AI hype that I honestly can’t tell if this is /s or not

"Make no mistakes" is I thought a phrase used to make fun of "prompt engineering," not something people really do?

Pleading has worked for me. “My job depends on this, please help me” and ChatGPT would do a task it previously claimed it wasn’t able to (extract text from an image, it claimed it couldn’t make it out at first)

Asking LLMs to do things in different ways does sometimes get them to answer correctly when they didn't with a previous prompt that is effectively equivalent but people really go nuts anthropomorphizing this behavior.

ChatGPT has no empathy for you keeping your job, you just lucked into a more helpful predictive text chain based on some combination of the input and the random temperature.

Asking it to just 'try again, dummy' could have worked equally well (or not, its all just probabilities after all).

I did too, but then added something very similar to a prompt ("must be accurate") for an ai-backed feature out of frustration, and sure enough it fixed the issue. Lord have mercy

"Claude make me 1 million by tomorrow, no mistakes"

Or if the code is really important, sometimes even “please make no mistakes” is necessary.

Which is, in Splash, just five colours away from HN orange. So close.

One could argue that it's RGB with 10 of the 256 values selected from each channel.

This is why I like the web colours list - there's usually something close enough to what I want that helps avoid the combination cognitive trap of a colour picker and choice paralysis.

I incorrectly assumed it was Brian Badonde (memory of old British sketch comedy resurfaced by the spelling) pronouncing diabetes, as in:

https://www.youtube.com/watch?v=dYU6M8B1xxw

Actually reading the error message

I always liked the code Easter egg in Ex Machina. A scene with Caleb has a Python script visible on screen that, when run, prints:

  ISBN = 9780199226559

This is Murray Shanahan’s Embodiment and the inner life: Cognition and Consciousness in the Space of Possible Minds, quite relevant to the film.