😅 holy shit, this church is based

Congratulations! … [Cries in Florida man tears]

deleted by creator

Tons of people already are. The following site is useful for searching papers using ai https://consensus.app/

Maaaaan… I could never run for office. I’m not a Nazi, but they’d find my old furry art in 12 seconds.

My resume has 4 to 5 jobs on it, single page. I leave out tones of slop, and include only the most relevant jobs for the position to which I’m applying.

If you don’t mind me asking, why don’t you like this other girl? Was she mean to you?

I’ll be honest, this is confusing as hell, so I might be misunderstanding.

I think it’s a little hypocritical that you want it to be a chill, no drama space with the bros, but you also want to exclude a girl because you see her as competition for the guy you like who is in this group.

I understand you had a bad experience with her, but you said that the guys don’t know that. From their perspective, you’re just excluding other girls for no other reasons than seemingly to be the only girl in the group and perhaps to have exclusive access to your crush.

Meanwhile: Christians

Probably if there is some sort of universal intelligence evaluating our actions and decisions, it would turn anyone entertaining this idea into an worm in their next life. The premise that the good fortuned should be passive to suffering, and enable it, out of some misguided moral calculus is absurd. You can’t game the system.

Ugh… I’m deep on the ai sphere, and this seems like a bad idea to me. Gpt (let’s face it, they are probably using open ai) can be deeply biased and arbitrary in it’s evaluations.

For example, “Two apples and four oranges,” might score better than: “4 oranges and 2 apples.” for inscrutable reasons. Say, if the question spelled out the numbers, and the LLM has a weighted bias to favor overall textual consistently, it might produces a reason to dock points apparently unrelated to that weight, such as: “incomplete sentence.” for the second answer, but not the first.

Students may also receive lower scores due to cultural biases towards certain phrases, and factors as straightforward as their name.

Finally, AI will hallucinate errors constantly if you ask it to evaluate text without any errors. Constantly. Consistently.

I believe Librechat would achieve your goals, but you’d need a PC or server to host it in. It supports all major API.

Kobold light might with as well, and doesn’t need to be hosted locally, but I don’t think it supports Claude haiku specifically, for unknown reasons.

Additionally, the official Claude api workshop is pretty good on desktop, but it only supports Claude.