Testing GPT-4 spatial reasoning and comprehension

Marton Trencseni - Sun 21 May 2023 • Tagged with gpt, gpt-4

I run experiments to determine whether, or to what degree, GPT-4 has developed an comprehension of spatial relationships. I find that it it significantly better than GPT-3.

GPT-3

Continue reading

Testing GPT-3 spatial reasoning and comprehension

Marton Trencseni - Sat 17 December 2022 • Tagged with gpt, gpt-3

I run experiments to determine whether, or to what degree, GPT-3 has developed an comprehension of spatial relationships.

GPT-3

Continue reading

How good an astrophysicist is GPT-3?

Marton Trencseni - Mon 12 December 2022 • Tagged with gpt, gpt-3

Here I will show a "conversation" with GPT-3 to gauge how good an astrophysicist — or an illusion of an astrophysicist — it is. I will focus on cosmology questions, because that's most interesting part of the field.

GPT-3

Continue reading

How good a particle physicist is GPT-3?

Marton Trencseni - Sat 24 September 2022 • Tagged with gpt, gpt-3

Here I will show a "conversation" with GPT-3 to gauge how good a particle physicist — or an illusion of a particle physicist — it is.

GPT-3

Continue reading

How good a Data Scientist is GPT-3? - Part II

Marton Trencseni - Sat 03 September 2022 • Tagged with gpt, gpt-3

I have further "conversations" with GPT-3, this time asking more difficult questions about real-world Data Science projects I have personally worked on.

GPT-3

Continue reading

How good a Data Scientist is GPT-3?

Marton Trencseni - Sun 31 July 2022 • Tagged with gpt, gpt-3

Recently I have been playing around with OpenAI's GPT-3 and I am very impressed by it. It reminds of the famous Arthur C. Clarke quote, “Any sufficiently advanced technology is indistinguishable from magic.” Here I will show a "conversation" with GPT-3 to gauge how good a Data Scientist — or an illusion of a Data Scientist — it is.

GPT-3

Continue reading