Read the piece on blog.eladgil.com ↗
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.
Their wordsAt this point, the only validated way of improving reasoning is to train models on larger data and make them bigger.
Their wordsSo it doesn't displace fine tuning because fine tuning has a very different purpose of pouring your preferences and basically demonstrating the task.
Their wordsI would say in three years this is going to look very different, especially if we find a way to deploy agent and to evaluate them and make them robust and reliable.
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.