AI Does NYT Connections
mikehearn.notion.site
AI Does NYT Connections
1–10 of 22 posts
Re: AI Does NYT Connections
#2Argh put a spoiler cover over today's at least!
Re: AI Does NYT Connections
#3Connections is a great game to test AI. It really relies on the ambiguity and loosely connected aspects of culture and language. I am shocked at how well o1-pro does.
Re: AI Does NYT Connections
#4This is nicely presented. I would like to see the prompts to the respective services, however. Did I miss them? The "side peek" would be a natural place for them.
Re: AI Does NYT Connections
#5Spoiler alert
Re: AI Does NYT Connections
#6Beyond being able to solve Connections, can a LLM generate (good/challenging/solvable) connections? Would be pretty cool to be able to generate a test set.
Re: AI Does NYT Connections
#7LLMs don’t have “intelligence”.
Re: AI Does NYT Connections
#8I'd love to see them try "Only Connect" puzzles which are _much_ harder.
Re: AI Does NYT Connections
#9These kind of tests (or may be all tests) should show *success rate* instead of a single pass/fail.
I believe Claude or even Gemini can succeed if system prompt is improved e.g. tell it to re-evaluate it's answer before finalising, can even tell it to do "thinking" within tags. I use claude like that and it often goes over it's answer and corrects itself within same reply. On the other hand it can also incorrectly assume it made a mistake and can sometimes uncorrect itself.
Edit: Using o1's step by step problem solving example from OpenAI blog post made Claude go step by step in similar depth too. Could even do that here to get better success rate in non-o1 models.
Re: AI Does NYT Connections
#10Hmm, isn't there like five lives before "ending"? So instead of doing a "perfect run" there should be chances, and feedback, such as "one missing", like a real human player?