Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Blog Pricing

Nicholas Andresen

๐Ÿ‘ค Speaker
498 total appearances

Appearances Over Time

Podcast Appearances

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

You're never stuck, you can always grab the best-fitting piece from each language and move on.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

It's just less bueno for everyone else.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

That's Thinkish.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

The model seems to grab whichever token fits best, optimizing for its own convenience.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

The problem is that we're the outsiders now.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

So how much stranger can Thinkish get?

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

To get a sense of that, let me tell you about King Alfred the Great.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

In 891 AD, King Alfred the Great completed his translation of the Consolation of Philosophy, one of the last great philosophical works of antiquity, written in Latin by Boethius, a Roman senator, while awaiting execution.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Here's one sentence.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Quote.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

This is English.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Old English, but English, connected to what you're reading right now by an unbroken chain of comprehension stretching back over a thousand years.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Watch the chain.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

In 1330, Chaucer's translation read, Blissful is at man at may seen ye clear welly of good.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

In 1556, Colville gave us, Happy or blessed is he that may see the shining fountain, or well of good.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

By 1973, Watts wrote, Happy is the man who may see the clear fountain of good.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Every person in this thousand-year chain understood their parents and children.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Yet we cannot understand Alfred, and Alfred would not understand us.

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Why?

LessWrong (Curated & Popular)
"How AI Is Learning to Think in Secret" by Nicholas Andresen

Languages change for many reasons.