I’ve been trying to put my finger on what it is that is happening when the robot writes stuff like “3 campuses, one app” example, I’m glad the author was able to identify it as chat context leaking through.
The other version of it is the robot over-indexing on some part of the prompt and leaving comments places. An example is I ask it to prefer integration tests using TestContainers, it starts adding comments to every new test saying “Real services, no mocks” or something.
And yes, I have a line in my *.MD saying not to do that.
LLMs love <a href="https://tvtropes.org/pmwiki/pmwiki.php/Main/SuspiciouslySpecificDenial" rel="nofollow">https://tvtropes.org/pmwiki/pmwiki.php/Main/SuspiciouslySpec... . You tell them not to do a thing, they make a point of saying they didn't do the thing.
And btw, if you have slop comments in your PR, you'll get a review from an agent (my company pay for it). I won't bother to read if you didn't bother either.
Eh, I'd prefer a opus5.5 review with consequent approval over one by a human which I have to wait 5 days for.
Ymmv, I also hate it when people dont read their own PR first though. But I know I've previously identified comments as LLM written which the dev... On further discussion definitely wrote themselves. So you gotta keep the false positives in mind.
It's partly a "Don't think of a Pink Elephant" problem. I've worked on several projects where I had to keep telling prompt writers to stop writing negative examples because the more you include the more its "attention" to them is all it has. Like telling a toddler not to do something and being surprised that is now all they can think about and they want to keep doing it. These prompt writers kept getting surprised that I'd delete all their negative examples and harshly worded "Don't do X" and "Never Y" and "NO: Z" sections they spend so much time on and got better results with smaller more focused positive example only prompts.
Hah! I also thought about it this way and ended up added a "purple elephant rule" to my pi prompt to discourage the behaviour, since I figured LLMs lean on metaphors so much.
Of course, I quickly reverted this change as purple elephants started cropping up in comments and other prose :)
Early versions of stable diffusion supported negative prompts and they never leaked because it would just down weight that stuff.
I don't understand why negative prompts never made it into the LLM world. If "no foo" and "dont do bat" don't work then just give me a separate textbox where i can put all my negatives!
weakfish · · focus · HN ↗
The other version of it is the robot over-indexing on some part of the prompt and leaving comments places. An example is I ask it to prefer integration tests using TestContainers, it starts adding comments to every new test saying “Real services, no mocks” or something.
And yes, I have a line in my *.MD saying not to do that.
JoshTriplett · · focus · HN ↗
orwin · · focus · HN ↗
And btw, if you have slop comments in your PR, you'll get a review from an agent (my company pay for it). I won't bother to read if you didn't bother either.
ffsm8 · · focus · HN ↗
Ymmv, I also hate it when people dont read their own PR first though. But I know I've previously identified comments as LLM written which the dev... On further discussion definitely wrote themselves. So you gotta keep the false positives in mind.
WorldMaker · · focus · HN ↗
jesse_ash · · focus · HN ↗
Of course, I quickly reverted this change as purple elephants started cropping up in comments and other prose :)
8n4vidtmkvmk · · focus · HN ↗
jesse_ash · · focus · HN ↗
demibabs · · focus · HN ↗
They just also really love to tell you about it.
8n4vidtmkvmk · · focus · HN ↗
I don't understand why negative prompts never made it into the LLM world. If "no foo" and "dont do bat" don't work then just give me a separate textbox where i can put all my negatives!