Christopher Olah

@chris-olah · 11 positions · On ppll ↗

Interpretability researcher at Anthropic, which he co-founded; before that at OpenAI and Google Brain.

Christopher Olah did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

What Christopher Olah says most about

neural networks 3

Deep learning will be understood very differently in thirty years than it is today.
LSTM architectures are designed so that retaining information over long time spans is their default behavior rather than something they must struggle to learn.

See all 3

AI and science 2

Understanding a machine learning model and understanding the data it operates on are inseparable tasks.
In a dimensionality-reduced visualization of high-dimensional data, the raw position of points carries no meaning on its own.

See all 2

ideas vs execution 2

An idea can look obvious in hindsight only because the insight that makes it obvious was itself the hard discovery.
Once a problem is correctly framed, the hardest part of solving it is already done.

See all 2