15

Want to wade into the sandy surf of the abyss? Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid.

Welcome to the Stubsack, your first port of call for learning fresh Awful you’ll near-instantly regret.

Any awful.systems sub may be subsneered in this subthread, techtakes or no.

If your sneer seems higher quality than you thought, feel free to cut’n’paste it into its own post — there’s no quota for posting and the bar really isn’t that high.

The post Xitter web has spawned so many “esoteric” right wing freaks, but there’s no appropriate sneer-space for them. I’m talking redscare-ish, reality challenged “culture critics” who write about everything but understand nothing. I’m talking about reply-guys who make the same 6 tweets about the same 3 subjects. They’re inescapable at this point, yet I don’t see them mocked (as much as they should be)

Like, there was one dude a while back who insisted that women couldn’t be surgeons because they didn’t believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I can’t escape them, I would love to sneer at them.

(Credit and/or blame to David Gerard for starting this.)

you are viewing a single comment's thread
view the rest of the comments
[-] ysegrim@furry.engineer 3 points 18 hours ago

@YourNetworkIsHaunted @StumpyTheMutt ... Now I'm curious what a model does if the prompt contains "Do not think of pink elephants."

[-] starsider@valenciapa.ws 3 points 12 hours ago

@ysegrim @YourNetworkIsHaunted @StumpyTheMutt in my experience that makes it much more likely to generate stuff related to pink elephants.

[-] BioMan@awful.systems 3 points 14 hours ago

This would actually be an interesting question for the more rigorous end of the mechanistic interpretability people to study. They decompose the system to find 'features' within different layers that are associated with different behaviors or concepts in the inputs and outputs, that activate or deactivate each other. Famous example being the time they identified a linear combination of activations in a layer that corresponded to 'the golden gate bridge' and when they reached in and kept their numbers high during the running of the model it would not stop talking about it regardless of the topic, even while acknowledging that its answers were incorrect for the questions at hand.

I actually would love to see what mechanistically happens to that feature when you put in the input 'do not talk about the golden gate bridge'.

[-] StumpyTheMutt@social.linux.pizza 4 points 18 hours ago

@ysegrim @YourNetworkIsHaunted Do LLMs dream of electric slop?

this post was submitted on 03 May 2026
15 points (100.0% liked)

TechTakes

2565 readers
87 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 2 years ago
MODERATORS