Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
the claude desktop is changing the behavior. every thread in the claude code now feels like a chat with a person more than a disposable chat.
i just reorganized the active chats by the way i would have organized the team. interesting.
@amorriscode@bcherny *subfolders to groups in the sidebar with particular threads.
Threads are grouped by the folder they are working with right now, so the subgroups im referring to are not folders but rather custom created groups of threads within the folder.
@garrytan That’s why “login with openai” would be epic. That’s exactly why the banks could’ve won it already but never did.
And there’s a lot more to come here.
@SherryYanJiang i don’t mind either personally, but the way i am building now is for the second and main reason for it is - questions don’t carry lots of context (still some guess game), whilst if the someone is using the product for a bit - the context is expanding and it’s more accurate
@dennismuellr same story here - every time i'm either hours into the run or cycle, or deep into intervals - i am convinced i can do so much.
when in fact i couldn't further out.