261–270 of 507 posts
The “cocktail” thing is real. A while back I tried to get DALLE to imagine characters from Moby Dick [1], but it completely refused. You’d think an AI company could come up with a better obscenity filter! [1] https://superb-owl.link/shapes-of-stories/#1513
Good gracious could I please just use an unfiltered model? Or maybe one which isn’t so sensitive?
> It looks like the safety filter may have taken offense to the word “Cocktail”! I'm definitely not a fan of these severely hamstrung by default models. Especially as it seems to be based on an extremely puritan ethical system.
Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
> encrypted and local of course Only for people who'd pay for that. Free users would become the product.
Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
I'm working on this! https://www.perfectmemory.ai/ It's encrypted (on top of Bitlocker) and local. There's all this competition who makes the best, most articulate LLM. But the truth is that off-the-shelf 7B models can put sentences together with no problem. It's the context they're missing.
Today I learned I own basically the same set of cookbooks as Simon Willison.
Earlier quoted context omitted.
I feel like the storage requirements are really going to be these issue for these apps/services that run on "take screenshots and OCR them" functionality with LLMs. If you're using something like this a huge part of the value proposition is in the long term, but until something has a more efficient way to function, even a 1-year history is impractical for a lot of people. For example, consider the classic situation o…
This is where Microsoft (and Apple) has a leg up -- they can hook the UI at the draw level and parse the interface far more reliably + efficently than screenshot + OCR.
> It looks like the safety filter may have taken offense to the word “Cocktail”! I'm definitely not a fan of these severely hamstrung by default models. Especially as it seems to be based on an extremely puritan ethical system.
Earlier quoted context omitted.
I’m not sure I would necessarily call YouTube a moat-creator for Google, since the content on YouTube is for all intents and purposes public data.
There is a difference between downloading a few videos and having access to ALL of them.
Ok, crazy tangent; Where agents will potentially become extremely useful/dystopian is when they just silently watch your entire screen at all times. Isolated, encrypted and local preferably. Imagine it just watching you coding for months, planning stuff, researching things, it could potentially give you personal and professional advice from deep knowledge about you. "I noticed you code this way, may i recommend this…
I bet meta is thinking of doing this with quest once the battery life improves.