ChatGPT-5 Pro is the first model to successfully do this non-puzzle consistently. GPT-5 Thinking and GPT-5 fail as every other model before has (except for, occasionally, Sonnet).
@emollick
-
Three AI Models Achieve Gold at Math Olympiad
By
–
To follow up on a comment: I think it is a big step forward, but not an unexpected one if you have been following the curve. Three models got Gold at the Math Olympiad last week. I am losing track on what massive advances mean. All the models are improving very quickly right now
-
Three AI Models Achieve Gold at Math Olympiad
By
–
I think it is a big step forward, but not an unexpected one. I am losing track on what massive advances mean. Three models got Gold at the Math Olympiad last week. All the models are very capable right now.
-
Randomness in AI evaluation makes reproducibility challenging
By
–
That is surprising, but there is a lot of randomness. If you try again from scratch, you may get better (or worse) results. It makes evaluation really hard.
-
GPT-5 Performance: Real-World Task Improvements Over Competitors
By
–
On the big picture: GPT-5 as a model is pretty much on the same curve as the other top labs. I'd expect the usual leapfrogging between Gemini, Claude, OpenAI, & Grok to continue. Where there are some big gains is that GPT-5 seems well-trained for real world tasks in new ways.
-
GPT-5 Model Variability and Transparency Issues Explained
By
–
You are likely going to see a lot of very varied results posted online from GPT-5 because it is actually multiple models, some of which are very good and some of which are meh. Since the underlying model selection isn’t transparent, expect confusion.
-
AI Independence: No Money, No Agreements, No Bias
By
–
People often ask about how I work with AI labs, and I think it is a good question: I take no money from any AI lab. I have no agreements besides NDAs. They don't see what I write in advance. (This isn’t limited to the labs, I never accept any sponsorship or ads for any writing)
-
GPT-5 Creative Writing Techniques and Prompt Engineering Strategies
By
–
Worth reading what GPT-5 wrote in the intro to my new post when asked to do something dramatic. The second image explains the tricks it used. https://
open.substack.com/pub/oneusefult
hing/p/gpt-5-it-just-does-stuff?r=i5f7&utm_medium=ios
… -
AI Independence: No Funding or Agreements with Labs
By
–
Nope – and no offense, it is an important question. I take no money from any AI lab. I have no agreements besides NDAs. They don't see what I write in advance.
-
GPT-5 Access: AI Creates Procedural Building Editor Without Code
By
–
I had access to GPT-5. I think it is a very big deal as it is very smart & just does stuff for you
— Ethan Mollick (@emollick) 7 août 2025
Full write up in comments, but this is “make a procedural brutalist building creator where i can drag and edit buildings in cool ways" & "make it better" a bunch. I touched no code pic.twitter.com/hnYV39FOOnI had access to GPT-5. I think it is a very big deal as it is very smart & just does stuff for you Full write up in comments, but this is “make a procedural brutalist building creator where i can drag and edit buildings in cool ways" & "make it better" a bunch. I touched no code