midnightbobarun

Every time there's any news or rumors about a new Gemini model, I cross my fingers and hope that it'll be the one that finally catches up to other big AI coding models. It hasn't happened yet, but I'm hoping this time it will... :')

That's definitely a cool and unique concept... nice

I also like the more browsers have built-in adblock, but so far I've never seen any of them copy uBlock Origin's "element picker" (the little eyedropper tool) feature... it's good for getting rid of annoying stuff on certain websites and only uBlock Origin seems to do it. :(

I think we have a sort-of-similar AI setup, except I use HTML files rather than markdown, and this is because I'm on macOS and it's easier to use "quick look" on HTML files than markdown (HTMl shows up nicely, markdown is just plain text). Also, I ask the AI to get rid of old documents and try to merge documents together, so that there's not as many documents cluttering up context.

As for motivation: I need to pay bills, all I can think is "I need to build more"... :'D

Didn't he get his way in the end? Java becoming the programming language of choice for Android happened when he was CEO.

Super-powerful (if rather pricy) Linux desktop that happens to play games while doing everything else... that man is living my dream :'D

The notes app has a search function, so I've never had any difficulty finding what I'm looking for

Very nice, I hope this means increased support for it in open source projects

I had to look at my phone's backup settings just now, there's not really all that much being backed up but there's some apps that I had no idea were being backed up at all (and I didn't think they made much sense either).

Anyway, for anyone who's using an Android phone, this is probably a good time to check and see what's getting backed up to Google, because some of that stuff is probably not necessary.

I use the notes app on my phone, the same way I've been doing for years and years... that's probably not an exciting answer, but it's worked for me.

Maybe I could pass it off to an AI and see if I benefit from that somehow, but... eh... the notes app has worked okay.

Probably anything that's not cost-effective to train AI for or, more likely, anything that's too subjective that AI can't do a good job regardless of how much data it's trained on.

What's "too subjective?" Well, take fashion, for example. Can you teach an AI to design clothes? Of course you can. Can you teach an AI to anticipate what will become trendy for the next year among teenagers? Probably not, just because it's hard to train a model to anticipate fleeting whims. You'd need someone who's really plugged into "the culture" to anticipate future trends, and that's more art than data science.

There's probably other examples I could give, but that's the one that comes to mind most.

The UI does look really nice, I think you did a great job with it

I'm kind of impressed how often they manage to do this. Claude Code and Grok Build do resets too, but nowhere near this often. And in an ironic twist for a big company with the infrastructure, Google Antigravity never seems to do resets like this at all (at least that I've noticed). I wonder how much this stuff costs OpenAI to do?

I might travel the world. On foot, if necessary (it will probably be necessary if I have no money).

I'd say any cheap mouse off Amazon that has a pleasing shape is usually good enough, but I've also never ranked above gold in any competitive PvP shooter, so there's that :')

I'm currently using a wireless ProtoArc mouse. Good shape, can adjust DPI on the fly, hasn't broken even after a year. I think it was like 30 bucks maybe?

Just a few requests of Opus on the $20 plan uses up my entire 5 hour limit... I don't even want to know what Fable would do.

I hope it goes through, if only to improve Claude usage limits a bit...

And I don't think there's that many people using Meta Spark (I might be wrong)

Regarding being "usefully critical": something I've noticed, and it seems to happen more with cheap or "instant" models, is that it will nitpick seemingly minor things. Often it's things that aren't even all that important to the point of the discussion, but it might fixate on it, and low-key argue about it (but in a circular "I'm not saying X but I'm not agreeing with Y" kind of way).

My theory is that sycophancy is just intended to prevent the AI from spiraling into a loop of ineffectually "arguing" or fixating on unimportant details, because it's both kind of annoying when it happens AND it's obvious that the model is spiraling and burning tokens uselessly when it decides to be uselessly critical.

I don't have a PSP to try it on, but that honestly looks really impressive. :o

Something I've noticed is that local models are giving better answers these days than they did a year or two ago, even if the size (in parameters and in the amount of RAM used) hasn't increased. I'm not familiar enough with the technical side of model training to explain how they're doing this, but I think in another couple of years, models that use up 48 GB will be able to squeeze out even more incredible performance.

Though on the level of something like Sonnet 5... well, maybe not.