As the title says, I updated the bot a day or so ago, so you can chat with it in the comments. It should now also support context, meaning it knows the whole comment chain. And you don’t have to tag it if you’re replying to it.
I’ve updated @Mistral to remember the whole tree of comments when replying to you, so it can do follow-up responses. You still have to mention it on every message, though. Example in the comments.
In this video, we recount an incident that occurred at OpenAI while researchers were trying to finetune GPT-2 to be as helpful and ethical as possible. It’s narrated that inadvertently flipping a single minus sign led GPT-2 to become the embodiment of a well-known cardinal sin.
Earlier this week I discussed an example of ChatGPT giving ‘placeholder’ answers in lieu of real answers. Below is an example of what that looks like. I could swear this didn’t used to happen, but it basically just ‘doesn’t’ answer your question. I’m interested how often other people see this behavior....
it loves getting a rut of suggesting the lamest 20 things it can possibly think of. mood board! gardening! volunteering! it’s a fucking supercomputer and that’s all it can do??...
Have any other regular users noticed that 4 seems to more and more only offer ‘placeholder’ logic in lieu of where the actually useful bit of code or important step would be?...