I had actually made an AI benchmark where in one test convo I asked various models to opine on this github.com/firasd/vibesbench…

Bill Clinton: "I think Congress made a mistake not protesting turning the Rose Garden into what looks like the entrance to Liberace's bathroom"

I've started to prefer food that is lightly seasoned as in the West. My dislike for spices & tadkas grows by the day.

🚨🚨Blinkit is not convinced that private labels are a profitable long term strategy Meanwhile Swiggy has gone all-in to scale its in-house brand Noice thearcweb.com/article/swiggy… Blinkit also has its own private label — Whole Farm & Savemore

Its not a new idea, but the lack of giant eccentric monumental architecture in Silicon Valley is a shame. You have lots of weird people with too much money, and yet only one place at the level of a solid midwestern oddball tourist attraction, and that was started in the 1880s.

Trump: If you’re in doubt about somebody's name from the Middle East, just say Mohammed, you have about a 65% chance. Hello, Mohammed. I've done it for years now. I’ve never been wrong.

One of my friends has become a lot more critical of Israel this year and showed me that he had even bought “One Day Everyone Will Have Always Been Against This” which is great but like…his copy should say “Second Edition”

When you order something spicy and it actually has a layered spice flavor profile instead of neon red chili oil thrown in it

Anne Hathaway, Dakota Johnson & Josh Hartnett try to decide which film is better — ‘Black Swan’ or ‘Fatal Attraction’. “When I think of an iconic Glenn Close performance & an iconic Natalie Portman performance, it's these two.”

“You don’t study for the spelling bee” is a deep and important aspect of American culture. I was at a baseball game discussing some young players with a buddy one time and he said to me offhandedly, “hard work is fine, but nothing beats talent.” Americans have this sort of sense that there’s something a little off about working really hard to get good at something that you’re not naturally good at. You’re never really going to be on the same level as the guy who has a natural talent. We have room in our hearts for scrappy little guys who work hard, but we are by default suspicious of grinders and strivers. If you were really meant to do it, then you’d be naturally good at it. You sign your kids up for little league, but you don’t take it too seriously unless they show remarkable early talent. Yes, this sounds sort of ridiculous if you take it too literally. No, nobody is saying that there’s any kind of practical test for this or that anybody should be excluded because we found out that they secretly studied too hard. But this is a part of American culture. And if you can’t understand it, then that just marks you out as foreign to that culture to an even greater degree.

I have a Continuous Learning benchmark where models attempt to learn to play chess. They are given a /goal of learning and improving playing against a Stockfish opponent in 200 games. They can choose the difficulty, take notes, whatever they like - except cheating (e.g. using a chess engine) of course. So far the improvement in Elo has been negative for Astra. Tiny bit positive for Opus, but could also be random. I've started Astra off sooner, so it finished its 200 games already, Opus is still playing. Site here to watch how they are doing: ai-learning-to-play-chess.su… The reason why this is interesting is that while we obviously don't have continuous learning, at the back of my mind I was thinking that maybe models can simulate it through self-scaffolding. Turns out not so much at least in this context. Perhaps it's a solvable problem and we don't need 'true' self-learning for models to learn in some way. ------- Just a note, the idea for the benchmarks belongs to someone else, but I don't want to use their name to give this more weight without permission.

Liveclip in ChatGPT… beautiful I just said sort by likes and the LLM just called a table_sort tool .. no need for the AI to write ad-hoc code I’m thinking of making this a open source MCP server so you can just run it on your localhost and have Claude Code, Codex etc use it