@bcherny FR: Claude sees remaining context in the current window and says, "I can ship x but not y in the remaining budget before we have to wait for 5h. Proceed?"
Resuming development after the window reset unnecessarily eats a lot of tokens. I'd rather ship small and compact.
I don't know when this /btw feature was launched in Claude Code, but it is absolutely delightful!
Also, discovering new features in the terminal is somehow more fun than in the app.
For frontier models, model personality is an invisible layer of the UX for consumer apps.
I conducted a 2-part eval of Gemini 3 vs. GPT-5.1 Thinking to see how their internal rewards handle prompt constraints.
Result: Gemini seems 2.3x token-efficient than GPT! Post below
Although GPT 5.2 is out, the idea here is to evaluate the "Thinking" architecture, and the structural bias here seems to persist across incremental model updates.
Same prompt, yet 2.3x token difference!
Part 1: https://t.co/FFSNV7tQHh
Part 2 about steerability coming soon!
@bcherny Thank you for sharing! Could you share more on how to get Claude to iterate on UI/UX for webapps? I often find that opus is great at backend out of the box but its first attempts for new ui features tend to be somewhat off. I send screenshots and logs to CLI and ask it to fix.
The biggest downside of taking @shreyas' product sense course is that I can never again work with anyone who doesn't understand these concepts.
This includes not just co-founders and product leaders, but probably also marketers and sales leaders.
@saxena_puru Agree that it is a strong business. What are your thoughts on valuation though, especially if we consider an increased macro risk or possibility of a broader drawdown?
For all of the most important things, the timing always sucks. Waiting for a good time to quit your job? The stars will never align and the traffic lights of life will never all be green at the same time. The universe doesn’t conspire against you, but it doesn’t go out of its way to line up all the pins either. Conditions are never perfect. “Someday” is a disease that will take your dreams to the grave with you. Pro and con lists are just as bad. If it’s important to you and you want to do it “eventually,” just do it and correct course along the way.
OPINION: For S.F. to survive the challenges we face, we need to redefine our urban landscape by drawing inspiration from successful cities like Tokyo.
https://t.co/FT55CUfX2p
We collaborated with Bard, an AI experiment by @Google, to optimize your coding workflow.
When you use Bard to help with coding, you can now export Python code to Replit. In your Repl, you can edit or test it to bring your ideas to life.
Try it out → https://t.co/IUPQZ4F9mv
@cisneroscapital @cullenroche@kyrill007 Sorry for a newbie question, looking to learn - why not a money market fund yielding ~5% while offering basically best possible liquidity?
Installing python on an m2 MacBook has been so painful for me that I am exclusively using Google colab for simple python3 projects. Would love to get a definitive guide that just works.
I’ve tried homebrew and the pip installs did not work!
@lennysan Congratulations on the growth! Great podcast. Considering the quality of the podcast, I would have never guessed that it’s only been a year. 🎉🚀
Paper: TPUv4 system has an optically reconfigurable network to assemble groups of 4x4x4 chips like legos (4x4x12? 16x16x16?). SparseCores help w/ embeddings. TPUv4 outperforms TPUv3 by 2.1x & perf/W by 2.7x, & has 4096 chips so ~10x faster overall.
.https://t.co/24gclhXpuQ