Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 — mentioned by ben_w

Tue, 17 Oct 2023 08:24:24 GMT

The numbers in Table 1 of this paper are mostly worse than I remembered, but I would also note that humans would fail the "can they reason?" standard I quoted, given the grades the species gets on several of the tests: https://arxiv.org/pdf/2304.03439.pdf Table 2 likewise shows significant weaknesses in GPT-4, worse than I remember, except on MED which was better than I remember it being capable of. > even if you define "logic" as "logical puzzles encoded in natural language" and not "the thing that allows an LLM to reason highly efficiently about what token comes next". I think this is a…

Paper and discussion history. A mention is not an endorsement.

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 — HN submission

Mon, 10 Apr 2023 23:34:58 GMT

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

44 points; 60 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 · HackerPapers discussions

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 — mentioned by ben_w

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 — HN submission