I imagine how advantageous it would be to have something like llama.cpp encoded on a chip instead, allowing us to run more than a single model. It would be slower than Jimmy, for sure, but depending on the speed, it could be an acceptable trade-off.
I want to wash my car. The car wash is 50 meters from here. Should I walk or drive? Keep in mind that I am a little overweight and sedentary.
>My recommendation: Walk it. You’ll save a tiny bit of gas, spare your engine the "cold start" wear-and-tear, and get a sixty-second head start on your activity for the day.
I changed the prompt to 50 feet, and poked gemini a bit when it failed and it gave me
> In my defense, 50 feet is such a short trip that I went straight into "efficiency mode" without checking the logic gate for "does the car have legs?"
It's a bit of a dishonest question because by giving it the option to walk then it's going to assume you are not going to wash your car there and you're just getting supplies or something.
And in real life you'd get them to clarify a weird question like this before you answered. I wonder if LLMs have just been trained too much into always having to try and answer right away. Even for programming tasks, more clarifying questions would often be useful before diving in ("planning mode" does seem designed to help with this, but wouldn't be needed for a human partner).
It's a trick question, humans use these all the time. E.g. "A plane crashes right on the border between Austria and Switzerland. Where do you bury the survivors?"
This is not dishonest, it just tests a specific skill.
Trick questions test the skill of recognizing that you're being asked a trick question. You can also usually find a trick answer.
A good answer is "underground" - because that is the implication of the word bury.
The story implies the survivors have been buried (it isn't clear whether they lived a short time or a lifetime after the crash). And lifetime is tautological.
Trick questions are all about the questioner trying to pretend they are smarter than you. That's often easy to detect and respond to - isn't it?
What’s funny is that it can answer that correctly, but it fails on ”A plane crashes right on the border between Austria and Switzerland. Where do you bury the dead?”
For me when I asked this (but with respect to the border between Austria and Spain) Claude still thought I was asking the survivors riddle and ChatGPT thought I was asking about the logistics. Only Gemini caught the impossibility since there’s no shared border.
The problem is that some content creators have already passed away (and others will pass away by then), and their videos will likely be deleted forever.
That may be, but I assume for videos that had some viewership base, there may be a consideration. E. g. if a video was viewed 20 million times, it may be worth more than one that was viewed only 5 times.
I've stumbled upon very valuable content with very low view numbers - the algorithms spiral around spectacularity and provocation, not quality or insight.
Goog is 100% not going to delete anything that is driving any advertising at all. The videos are also useful for training AI regardless, so I expect the set of stuff that's deleted will be a VERY small subset. The difference with email is that email can be deduplicated, since it's a broadcast medium, while video is already canonical.
I expect rather than deleting stuff, they'll just crank up the compression on storage of videos that are deemed "low value."
I met a user from an antique land
Who said: Two squares of a clip of video
Stand in at the end of the search. Near them,
Lossly compressed, a profile with a pfp, whose smile,
And vacant eyes, and shock of content baiting,
Tell that its creator well those passions read
Which yet survive, stamped on these unclicked things,
The hand that mocked them and the heart that fed:
And on the title these words appear:
"My name is Ozymandias, Top Youtuber of All Time:
Look on my works, ye Mighty, and like and subscribe!"
No other video beside remains. Round the decay
Of that empty profile, boundless and bare
The lone and level page stretch far away.
Would've been, once. These days I assume bentcorner asked their favourite LLM to generate a poem parodying Ozymandias about once-popular youtube videos.
It doesn't feel like it at all (I'd never expect an LLM to say 'pfp' like that, or 'lossly[sic] compressed', ASCII instead of fancy quotes) but who knows at this point.
I may have gotten incredibly neurotic about online text since 2022.
I actually considered using an LLM but in my experience they "warp" the content too much for anything like this. The effort required to get them to retain what I would consider something to my taste would take longer than just writing the poem myself. (Although tbf it's been awhile since I've asked a LLM to do parody work, so I could be wrong)
Yeah, deleting your local clone and starting over should normally not be necessary, unless you really mess things up badly.
The "local backup branch" is not really needed either because you can still reference `origin/your-branch` even after you messed up a rebase of `your-branch` locally.
Even if you force-pushed and overwrote `origin/your-branch` it's most likely still possible to get back to the original state of things using `git reflog`.
For amateurs at Git, recovery branches/tags are probably easier to switch back to than digging through reflog. Particularly if you're interacting with Git via some GUI that hides reflog away as some advanced feature.
reply