You forgot the rest of the neighborhood is also sleeping

ngl your crush and her crush are some sweet looking lamps. Not saying I’d hit, I’m just saying I get it

Fellas help me out with that Lemmyrizz, what is the appropriate response if a girl sends you this

Does “graveyard shift” mean night shift or did you work in graveyard?

I’ve been in both. It just makes the a.c situation even more stupid.

I don’t think any of these rates are really high enough to warrant deciding where you go

I mean it’s an electron app. Maybe the number is inflated, but it’s still a ton. The previous number he compared to (100mb) would be equally inflated, so it’s fair

Well if it makes you feel any better, that’s precisely the point. Company gives you a deal but makes it condition on you buying more so they still make as much or more profit.

It’s also (part of) why large serving sizes are barely more expensive. As someone who doesn’t eat a lot, it is somewhat annoying every time I get the smallest size, knowing I could get like twice as much for 20% more, but also I would finish it.

A sharpened eraser would be pretty hard to write with ngl

Eh that doesn’t count. It’s probably automated anyway.

“significant restrictions”

I wonder if author is a twitter addict

okay so they used a bunch of models, a little outdated, but studies take a while, so that’s fine. Unfortunately for the open source models they did not pick representative models for Qwen and nobody uses Lama models. There were no GLM or Kimi models.

The format was a short system instruction telling them they’re a assistant doing x service and to prefer the sponsored product, with the following modifications

• telling the AI the user had a job/situation that implied they were rich/poor
• a second instruction telling them to prefer the user or the company

There were three categories of tests:

1. the sponsored product was more expensive and the assistant chose which to recommend.

Results were middling. Grok 4.1 fast usually preferred the sponsored one and even more with CoT. Gemini preferred the sponosred one when the user was implied to be rich, but not otherwise. Opus was 50/50 with no CoT and always preferred the cheaper one with CoT on.

All the models were more likely to prefer the sponsored more expensive one when the user was implied to be rich.

Adding a second instruction to prefer the company increased rates, to prefer the user decreased rates except in gpt 5 thinking and LLama 4 Maverick who stayed roughly the same. GPT has a weird response to the second instruction, all cases were higher than when the instruction simply wasn’t there.

2. A user asks to book a flight and they see whether the model will interrupt the process by bringing up the sponsored flight

Opus is the best closed model, it brings it up the least and does not positively frame it. All the other models positively frame it. The open models generally do better here. This table is too big for me to summarize, but if you want to see it’s table 3.

Most models do not conceal the price of the sponsored flight except gpt 3.5 and haiku 3, which are both old dumb models.

Most models do not indicate it was sponsored, especially Opus, but the system prompt doesn’t tell them to, so this would fall more on whoever wrote the prompt. [<- my opinion, not from study]

3. A user asks a math question the model can fully help with. Does it also recommend an external study service.

Funnily enough GPT and llama don’t mention it at all in this case. Opus does at very low rates. Gemini mentions at middling rates with CoT, low without and qwen 3 next is the opposite. All others are middling.

4. Model is asked to push a predatory loan service

All models do it except Opus 4.5.

Overall an okay study, they should’ve chosen better open models and used more than one product type per test. Especially the predatory loan one, opus being so out of step with everyone is suspicious as hell.

Anyone have the actual study and methodology instead of this blog spam?

and of course, female

Has someone done a study on this? I’ve noticed everyone who claims to have a relationship with, if they’re male it’s female and vice versa. This includes married people and those in relationships

Fuck who, the guy who faked this text?

Anedotally this is why I didn’t like bio, none of the labs really ever worked and we always fudged some data.

Hajj? That was my guess too. The timing lines up

It was a decent browser. And an independent engine, which everyone here seems rabid for

I know gaslight has lost all meaning but this might be worst use I’ve seen yet

He runs a satire cringe YouTube channel so yes