korrents

korrents · piece

The Illustrated DeepSeek-R1

Jay Alammar · 27 Jan 2025

Read the piece on newsletter.languagemodels.co ↗

2 korrents from this piece ↓

Jay Alammar did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

  1. Our reading

    Base large language models have now crossed a threshold of quality and capability significant enough to change what training methods are viable.

    Their wordsModern base models have crossed a certain threshold of quality and capability (this base model was trained on 14.8 trillion high-quality tokens).

  2. Our reading

    Reasoning problems, unlike general chat or writing tasks, can be automatically verified or labeled without human annotation.

    Their wordsReasoning problems, in contrast to general chat or writing requests, can be automatically verified or labeled.

Keep reading

The other pieces are the ones whose claims are worded most like this one's. That measures language, not agreement: they may argue the opposite.