whoistraitor

Yeh it’s strange it includes cockney so prominently. It isn’t really very present unless you spend time around the various gentlemen frequenting sports pubs and pie and mash shops in east London, or if you take a black cab very often. I’d say the “roadman” dialect, mixing cockney and Jamaican patois, plus grime vibes, is FAR more common. I’ll hear it everyday wandering around South and east London. I guess it’s a London dialect so it’s in that umbrella,… but how come cockney gets such a fat slab of land?

It’s remarkable we’ve hit a threshold where so much can be done with synthetic data. The reasoning race seems an utterly solvable problem now (thanks mostly to the verifiability of results). I guess the challenge then becomes non-reasoning domains, where qualitative and truly creative results are desired.

IMO first-or-not is moot. It’s estimated that around one billion people speak English to a reasonably fluent level. Included in that is many of the commonwealth countries in which English often holds second spot as a lingua franca (eg. India). It’s an incredibly global language.

Perplexity is listed, but do they actually abide by llms.txt? And how can we prove they do? Is it all good faith? I wish there were a better way.

The general message here seems to be that inference-time brute-forcing works as long as you have a good search and evaluation strategy. We’ve seemingly hit a ceiling on the base LLM forward-pass capability so any further wins are going to be in how we juggle multiple inferences to solve the problem space. It feels like a scripting problem now. Which is cool! A fun space for hacker-engineers. Also:

> My mental model for LLMs is that they work as a repository of vector programs. When prompted, they will fetch the program that your prompt maps to and "execute" it on the input at hand. LLMs are a way to store and operationalize millions of useful mini-programs via passive exposure to human-generated content.

I found this such an intriguing way of thinking about it.

Curious: what kind of problem domain to you work on? I use LLMs every day on pretty hard problems and they are always net positive. But I imagine they’re not well trained on material related to your work if you don’t find them useful.

It is probably the most reliable yeh, tho spending time here I’ve grown increasingly aware that the great firewall is more than aware of this vpn traffic, even if it’s wrapped up to look like normal traffic. They periodically will seem to ‘dial down’ the internet, especially at politically sensitive times. They are fully aware great swathes of the populace and visitors use VPNs, and they choose to allow it. They’d rather control and monitor than inspire even more opaque channels.

Don’t know what OP might suggest but my first take is: never allow unstructured output from one LLM (or random human) of N privilege as input to another of >N privilege. Eg, use typed tool/function calling abstractions or similar to mediate all interactions to levers of higher privilege.

Ah apologies I misread the architecture. But it does fit the spirit of finding disproportionately higher performance in smaller networks. Still promises of finding smaller sub networks. Running on mediocre mobile devices doesn’t seem a dream when stuff like this is released. Exciting!

Ie. A form of perverse incentive or the cobra effect. Endemic to capitalism, especially in infrastructure.

You can use HuggingFace, PerplexityAI, Anyscale, TogetherAI. There are a bunch of options. Many offer OpenAI compatible APIs too.

What I’d love to see is a rundown of new efficiencies in generative AI. With things like quantization and specialized transformer hardware, the costs will hopefully be less shocking in the future. And fwiw, I don’t find the article’s stats very shocking anyway. At least it’s a net win type of game, whereas the previous environmental bugbear, PoW crypto, was entirely premised on net-energy loss.