logoalt Hacker News

teknologist • today at 6:30 AM • 5 replies • view on HN

Theo seems to dislike anything that isn't Anthropic Claude. Suspicious, to say the least. On CursorBench, a good measure of real-world coding tasks, Gemini 4 Carbon comes out top: https://cursor.com/evals


Replies

LiamPowell • today at 6:53 AM

Every time I see a Theo tweet he's judging something on the most absurd metrics. Today for example, he was saying Astra 6.2 is bad because when he gave it a single line prompt telling it to create a new level for a game it used a name for the level that he'd seen before. Judging a model on how often it reuses a name is one of the most ridiculous benchmarks I've ever seen.

As far as I can tell, all his judgements are based on similarly absurd metrics, I don't know why people treat his preferences as valuable.

ywvcbk • today at 12:30 PM

They have excluded all OpenAI models, though? Of course I doubt they'd have the highest scores but likely would be most price efficient.

➕ show 1 reply
spprashant • today at 2:33 PM

I do not like Theo, but he is transparent about his OpenAI bias. He criticizes Anthropic frequently - mostly for their hostile closed-garden policies.

knollimar • today at 11:34 AM

I’m not sure Claude favoritism is fair; he loved OpenAI for a while. He just has really arbitrary and frankly bad takes imo