(free link, no paywall): https://t.co/tTXoD1rOae
pip install llm-evalgate https://t.co/DT4MinGgzw
Would genuinely like to hear what you find if you run it.
I shipped an "honest" regression gate in my open-source LLM eval library.
Then I measured how often it failed builds when nothing had actually regressed.
15%. One clean PR in seven.
Here is the bug, and why it is probably in your eval too.
I built a tiny economy where 5 creatures each think on a different lab's small model. You play as a trader. Then the economy learns, and your edge decays on screen.
@huggingface x @Gradio Build Small. Play it (and ❤️ the Space if it makes you smile). https://t.co/lTthAsXW2g
Weekly Portfolio Rotation (March 16, 2026)
Both systems scored. Positions set for Monday.
Macro regime: transition. Yield curve positive, VIX elevated. Real assets still leading.
Full breakdown below. https://t.co/tfvg6uUwzF
“If you’re going to live a long time, you have to keep learning. What you formerly knew is not enough. If you don’t adapt, you’re like a one-legged man in an ass-kicking contest.”
—Charlie Munger
@PradeepBonde Or in my case, finding a style that allowed me to live a lifestyle I wanted was the hard part. If you really don't want to blow up risking 0.1%/trade can last you awhile until you find a strategy that suits you.
Maybe I'm just slow, but I found that, in learning a skill, focused active repetitions are key.
Applied to my former students starting a career in data science, partners that ended up developing consistent trading, and myself in designing strategies.
@a_abayomiola Hey Yomi, just found this post. As for other places, not at the moment due to being tied down to research projects. But here's the shortest video source I liked on the topic https://t.co/6CZ9XQfcOq
CEO of Renaissance Technologies on the importance of recognizing talent and why a corporate bureaucracy could not.
"When I was at IBM, there was this attitude that programmers were like plumbers. If you need a big project done, just get more programmers. But I knew that some programmers were, like, ten times or more productive than others. I kept pushing IBM management to recognize this fact. But it did not.
I remember being in a managers meeting and some guy from corporate was explaining how they created something called their headlights program. The goal was to identify the best programmers in the company and pay them 20 percent more. Now, I figured this guy from corporate was making, like, $300,000 a year.
I raised my hand and suggested they increase the pay of their best programmers to $400,000 a year. And he was stunned. He said, "What? More than me? You've got to be kidding me. Well, if the guy's Bill Gates." I said, "No, Bill Gates was making, like, 400 million per year. Not 400,000." Anyway, they just didn't get it.
We don't make that mistake. We pay our programmers a ton in accordance with the value we place on the infrastructure they produce."
Had a friend make a decision to expand his business. This framework helped - Navigating Choices: The Philosophy of 1-Way vs 2-Way Doors in Decisions https://t.co/VS0viSEXSs
American hedge fund billionaire Bill Ackman is a big fan of self-studying investing.
"You can learn investing by reading books."
Here is the 11-Book-List that he recommends to everyone who wants to learn about Investing👇