Aidan

His tweet says it was his campaign and personal email, both of which are separate accounts from his house.gov email. But he probably uses his personal email for work

Apple’s fate is to be the American Sony

And it’s not an open palm gesture, you point only your index finger up. Otherwise it looks like you’re just waving at someone

I love Wen and I hope she has all the pizza she could ever want

You can have it generate shitty code and then compare it against examples it finds online to iterate that code. Also, it was trained on the whole internet, including those good solutions, and can often reproduce them on its own. but you have to tell it, explicitly, to do all this to make better code, rather than just asking for the code.

The story is too on-the-nose even for an onion article. “REPRESENTATIVE GOOD SAYS REPRESENTATIVES BAD”

I don't agree that ChatGPT has gotten dumber, but I do think I’ve noticed small differences in how it’s engineered.

I’ve experimented with writing apps that use the OpenAI api to use the GPT model, and this is the biggest non-obvious problem you have to deal with that can cause it to seem significantly smarter or dumber.

The version of GPT 3.5 and 4 used in ChatGPT can only “remember” 4096 tokens at once. That’s a total of its output, the user’s input, and “system messages,” which are messages the software sends to give GPT the necessary context to understand. The standard one is “You are ChatGPT, a large language model developed by OpenAI. Knowledge Cutoff: 2021-09. Current date: YYYY-MM-DD.” It receives an even longer one on the iOS app. If you enable the new Custom Instructions feature, those also take up the token limit.

It needs token space to remember your conversation, or else it gets a goldfish memory problem. But if you program it to waste too much token space remembering stuff you told it before, then it has fewer tokens to dedicate to generating each new response, so they have to be shorter, less detailed, and it can’t spend as much energy making sure they’re logically correct.

The model itself is definitely getting smarter as time goes on, but I think we’ve seen them experiment with different ways of engineering around the token limits when employing GPT in ChatGPT. That’s the difference people are noticing.

I live near the former Holmdel Bell Labs complex. It’s an amazing building. It was sadly left in disrepair for decades until a developer bought it a few years back and turned it into a corporate office space with a mall at the ground floor. I got my Covid shots there.

This is one of the problems with using country TLDs. They look cute, but when you buy it, you may not realize who controls it. Lemm.ee is similarly in a precarious position.

I really wish we could all agree to stop using country TLDs for this

Someone close to me is a HS teacher. During covid, the schools changed their policy from “no phones in class ever” to “you can have your phone in class but you’d better only use it to help with classwork or in an emergency.”

They’ve been trying to reverse the policy back to how it was, but it’s hard to get all the kids to believe that they can’t do this anymore. They don’t take the threat of punishment seriously because everyone is doing it now.

Even if you manage to deal with the phone issue, the school gives kids chromebooks now to do their work on. The student wifi network seemingly has no restrictions, since the teachers sometimes need to have them watch something on YouTube or Netflix.

So kids, during class, watch Netflix on their Chromebook instead of paying attention.

In about a year we’ll probably have that anyway. Practices like that will emerge as people get more experience running fediverse servers, and then they’ll get adopted by people trying to do what’s known to work

They sell your data and don’t feel bad. Why should you feel bad about selling your data?