Viewing profile — mlb_hn

Our GCP is down

nice overview of progress over time. are there quant metrics for the sim capabilities or is it mostly vibes?

he was good people

yeah, that's a very big caveat - haven't checked neo 20b yet. I've had a hard time getting the AI21 models to use it and those are also pretty big so it's interesting why sometimes…

definitely. also works on text translation/comprehension like emojis! https://aidungeon.medium.com/introducing-ai-dungeon-translat... . For actual benchmarks, scratchpad improves G…

I get the tokenization argument and it may influence it a bit, but I suspect the n-digit math issue has to do more with search the way it samples (in the bpe link gwern references …

Couple things there where you can see if it improves with the prompt/formatting. E.g. with Davinci (and J a bit but didn't test too much) you can get bette results by: - Using few-…

An alternative of that is as Oppenheimer once said, sometimes things are secret because a man doesn't like to know what he's up to if he can avoid it

This has been a systemic issue reported on for years; e.g. reported by the Intercept in 2017 [1] and Atlantic in 2019 [2]. Not really made clear from the story considering the Econ…

I think that goes back to a Karpathy quote [1], don't know where he got it from [1] https://twitter.com/karpathy/status/961307010246492160

My thinking there wasn't because of BPEs, I think it's a graph traversal issue.

Also, better prompt design if you have make implicit meaning explicit can improve the WiC score ( http://gptprompts.wikidot.com/linguistics:word-in-context ) and ANLI score ( http:…

Just priming an immediate availability response is likely going to get poor results. On the other hand, this does bring up an important point, which is that few people have been sy…

Great article. It's worth considering the Japanese reaction to the bomb - people thought it was cluster munitions or other conventional explosives leading to them taking sub-optima…

I don't think it's going to be about a single prompt; reverse engineering multiple prompts interacting with themselves is hard. There's a lot of cool things to be done with: (a) cr…

I think it would be jumping to conclusions to say because the military has vulnerabilities that the entire military industrial complex is a fraud. Pieces of it certainly are sub-op…

That's the dataset used in the paper.

Leadership in the US Government wasted a lot of time trying to play down the pandemic [1] as did large (conservative) news organizations [2]. Both are now trying to blame China, ar…