I found it such a hassle to keep locked down I gave up. Like, he'd be so aware that he'd find ways to watch me enter the PIN code when adjusting the settings. I'd have to be ever-vigilant and I got tired of it.
I am genuinely currious. With such terrible uptime... is it really just a series of "oops, we need to fix that" or is it that they just keep hitting a capacity wall and have to drop service until they add capacity or reduce usage?
I wonder if you have, but that normally what dreams provide is often just delivered subconsciously. You might be regarding a lot of great ideas as having occured when you were awake even though maybe some would never have come had you not slept/dreamt on them.
I hear you. I've been slowly building up my own tool (linked above) and keep feeling like someone is going to soon release something that a lot of people will agree should be an independent standard. I'm reluctant to host it with someone else so it needs to be opensource. But then again what I've got is working well for me.
I really want to try this approach. I'm curious because this has not been my experience at all. I created https://github.com/flippyhead/ai-brain mostly just for myself and a few friends use it. But so far, telling the AI (via CLAUDE.md) to look for relevant memories and to think about when and how to save them has worked very well. It can create structures based on decided priorities, notes for the future, that feel like they'd be very different if it was just trying to summarize everything.
I feel like we need an acronym for this kind of comment. I am pretty sure approximately 100% of HN posts now include at least one comment where someone, somehow, knows that an article is written by AI and resents it.
For Claude we have the ever present "you are absolutely right" and this is like it's human mirror.
Something like TLDR; but meaning "uhg, written by AI".
I'm sure it's me being an idiot, but once again I spent 20m trying to figure how to do a specific thing in google-land and still haven't figured it out. Even if I did set it somewhere, I see things like "Setting a budget does not cap resource or API consumption" with a link to a bunch of documentation I have to analyze.
I can't keep up with how fast things are changing. I built this to scan my AI dev sessions chats, search various places I frequent, and recommend tooling, libraries and all kinds of other things I might want to incorporate into my development practices.