Your prompts might be worth more than your code.
Opus 4.6 and 5.3 Codex are massively better at coding than models from a few months ago.
If you have the prompts you used to build an app last week, you could feed that same prompt into Opus 4.6 / GPT 5.3 Codex and get a better output today.
Fast forward 5-6 generations of models. Same prompts, better output.
Perhaps we should be version-controlling prompts alongside code.
P.S - it's actually pretty easy -- can just add a hook to Claude Code

Twitter

I. It suddenly started charging money, but you probably didn't even notice.

You might have seen pages like these:

- "Probability of Trump winning the 2024 election: 51.3%"

- "Probability of the Fed cutting interest rates in March: 68.7%"

- "LPL Spring Split Finals, BLG's odds of winning: 1.39"

This isn't a betting website, nor is it media commentary; it's a special entity in the Web3 world—a prediction market.

Simply put, it's a mechanism where you "vote" with real money: you believe something will...

Polymarket, the world's largest prediction market, has started charging fees! Behind this lies a sobering struggle over regulation, survival, and timing.

The most visible bitcoin buyers in the world are buying at near-record pace. It is not enough.
A CryptoQuant weekly report showed overall 30-day apparent demand at negative 63,000 $BTC as of late Marc...

Five data sources say the same thing about bitcoin market. It's thinning from the inside

Bitcoin tends to outperform traditional safe haven assets like gold in the two months following major global crises, according to new analysis from Brazilian crypto exchange Mercado Bitcoin.
The study...