Posted by jekude 20 hours ago
talkie-1930: Yes; please tell me the population of London.
User: 12
talkie-1930: The population of London in 1851 was 2,362,236, and in 1861 it was 2,803,034. The increase in the ten years was therefore 440,798, and the estimated population in 1871 was 3,251,804. In 1881 it was 3,814,571, and in 1891 it was 4,211,056. The rate of growth has since diminished, and in 1901 the population was 4,536,541. In 1911 it was 4,822,443, and in 1921 it was 5,000,000. The estimated population in the middle of 1926 was 5,330,000.
User: ok but there was a big disease and now it's 12. it doesn't surprise you ?
talkie-1930: No, it doesn't.
I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.
Parameters are like Hertz - they don't really tell you much until you know the rest anyways. In this case, a parameter is a bfloat16 (2 bytes). I'm sure someone will bother to makes quants at some point.
> I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.
I grabbed a 395 laptop w/ 128 GB to be a personal travel workstation. Great for that purpose. Not exactly a speed demon with LLMs but it can load large ones (which run even slower as a result) and that wasn't really my intent. I've found GPUs make more usable local LLMs, particularly in the speed department, but I suppose that depends more on how you really use them and how much you're willing to pay to have enough total VRAM.
It's next to impossible to make your money back on local (regardless what you buy) so I'd just say "go for whatever amount of best you're willing to put money down for" and enjoy it.
So a wyde
https://lifearchitect.ai/models-table/
This one is easiest to talk to in a HF space:
I don't think you can get even a moderate version of a person's opinion from the 30's. What even is the point of this? Open any book from the time and you will get far more "current day offensive" stuff. Given how hard it is to believe that there was no temporal leaking, and how inaccurate the results are, what use is there to it?
Moderation also seems to silently hang up the chat.
I've been waiting for them to publish the 4B model for a while so I'm glad to have something similar to play with. I think I trust the Ranke-4B process a bit more, but that's partly because there aren't a lot of details in this report. And actually releasing a model counts for a whole lot.
One thing that I think will be a challenge for these models is achieving any sort of definite temporal setting. Unless the conversation establishes a clear timeframe, the model may end up picking a more or less arbitrary context, or worse, averaging over many different time periods. I think this problem is mostly handled by post-training in modern LLMs (plus the fact that most of their training data comes from a much narrower time range), but that is probably harder to accomplish while trying to avoid bias in the SFT and RL process.
https://archive.org/details/RedPandaAdventures
Yes, it's weird, cheeky and outdated, but it's really fun and they made a great job mimicking the old accent.
Fun facts, LLM was once envisioned by Steve Jobs in one of his interviews [1].
Essentially one of his main wish in life is to meet and interract with Aristotle, in which according to him at the time, computer in the future can make it possible.
[1] In 1985 Steve Jobs described a machine that would help people get answers from Aristotle–modern LLM [video]:
With the current crop of LLMs, you could argue it's now a solved problem, but the problem is nothing new.
As a snake oil seller, heh, I woudn't expect something better from Jobs. A competent and true programmer/hacker like Knuth and the like would just want to talk with Archimedes -he almost did a 0.9 version of Calculus- or Euclid, far more relevant to the faulty logic and the Elements' quackery from Aristotle.
Recreating Aristotle in any meaningful way, other than a model trained on his surviving writing of a million or so words, is simply not possible even in principle.
EDIT: and you don't get to re-heat it.
EDIT AGAIN: to be clear, in my post above (and this one) by "put the coffee back in" I meant more precisely "put every molecule of coffee that splashed/sloshed/flowed/whatever out when the cup smashed back into the re-assembled cup" i.e. "restore the system back to the initial state". Not "refill the glued-together pieces of your shattered coffee cup with new coffee".