ELO

Article

ELO is a recurring concept in the Astral Codex Ten archive, appearing 2 times across 2 issues between April 04, 2022 and May 08, 2023. The archive places it in contexts such as “that just continues the trendline in ELO I just drew based on MCTS bots”; “Elo , a scoring system originally from chess which measures which of two players wins more often”. It most often appears alongside 2013, Agricultural Revolution, AI.

Metadata

  • Category: Concepts
  • Mention count: 2
  • Issue count: 2
  • First seen: April 04, 2022
  • Last seen: May 08, 2023

Appears In

Source Context

Recovered passages from the original issue text. When the raw archive preserved outbound links inside the source passage, they are listed directly under the quote.

April 04, 2022 · Original source
The impact of GPT-3 had nothing whatsoever to do with its perplexity on Penn Treebank . . . the impact of GPT-3 was in establishing that trendlines did continue in a way that shocked pretty much everyone who'd written off 'naive' scaling strategies. Progress is made out of stacked sigmoids: if the next sigmoid doesn't show up, progress doesn't happen. Trends happen, until they stop. Trendlines are not caused by the laws of physics. You can dismiss AlphaGo by saying "oh, that just continues the trendline in ELO I just drew based on MCTS bots", but the fact remains that MCTS progress had stagnated, and here we are in 2021, and pure MCTS approaches do not approach human champions, much less beat them. Appealing to trendlines is roughly as informative as "calories in calories out"; 'the trend continued because the trend continued'. A new sigmoid being discovered is extremely important.
May 08, 2023 · Original source
...up along some Pareto frontier ; they can’t be more helpful without sacrificing harmlessness, or vice versa. Here, Anthropic measures helpfulness and harmlessness through Elo , a scoring system originally from chess which measures which of two players wins more often. If AI #1 has helpfulness Elo of 200, and AI #2 has helpfulness Elo of 100, and you ask them both a question, AI #1 should be more helpful 64% of the time. The graph abo...