Navid Mostafavi

hardware engineer | software engineer | quiet observer [he/him/his]

[Crémieux @cremieuxrecueil]

Eli Lilly has done it.

They've gone and made what seems to be a powerful, permanent gene therapy for LDL cholesterol.

That means they'll be able to effectively prevent most heart disease with a single infusion!

[Lenny Rachitsky @lennysan]

"Using coding agents well is taking every inch of my 25 years of experience as a software engineer, and it is mentally exhausting.

I can fire up four agents in parallel and have them work on four different problems, and by 11am I am wiped out for the day.

There is a limit on human cognition. Even if you're not reviewing everything they're doing, how much you can hold in your head at one time. There's a sort of personal skill that we have to learn, which is finding our new limits. What is a responsible way for us to not burn out, and for us to use the time that we have?" @simonw

[SportsCenter @SportsCenter]

Madden Orlovsky had a heartfelt message for his family and friends in honor of World Autism Awareness Day 🥹

This was a special moment for all of us at ESPN. Thanks, Madden and @danorlovsky7 ❤️

[Michał Podlewski @trajektoriePL]

Cardiologist wins 3rd place at Anthropic's hackathon. Out of 13,000 applications. Built in 7 days by Michał Nedoszytko MD. Coded day and night - in the hospital, in the cloud, while flying from Brussels to San Francisco.
A few years ago, it would have been impossible for a doctor to build this alone in just a couple of days. AI changed that.

The project is called https://t.co/wAliajqjVF. It is an AI agentic care platform for patients. Including reverse AI scribe it is a companion that guides the patient from the moment they leave the doctor's office.

Powered by the massive context window of Opus 4.6, it allows patients to explore their full medical history, connected devices, Evidence Based resources and external data sources — all in one place.

Today, the barrier to entry has vanished; even a practicing physician can build an application from scratch.

[BURKOV @burkov]

LLMs process text from left to right — each token can only look back at what came before it, never forward. This means that when you write a long prompt with context at the beginning and a question at the end, the model answers the question having "seen" the context, but the context tokens were generated without any awareness of what question was coming. This asymmetry is a basic structural property of how these models work.

The paper asks what happens if you just send the prompt twice in a row, so that every part of the input gets a second pass where it can attend to every other part. The answer is that accuracy goes up across seven different benchmarks and seven different models (from the Gemini, ChatGPT, Claude, and DeepSeek series of LLMs), with no increase in the length of the model's output and no meaningful increase in response time — because processing the input is done in parallel by the hardware anyway.

There are no new losses to compute, no finetuning, no clever prompt engineering beyond the repetition itself.

The gap between this technique and doing nothing is sometimes small, sometimes large (one model went from 21% to 97% on a task involving finding a name in a list). If you are thinking about how to get better results from these models without paying for longer outputs or slower responses, that's a fairly concrete and low-effort finding.

Read with AI tutor: https://t.co/MipHHO6rjX

Get the PDF: https://t.co/XQrqiaGwIO

[j. patrick coolican @jpcoolican]

Minnesota Republican state senator 👇 from south suburbs.

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.

My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.

So, here goes.

[Steven Pinker @sapinker]

Bombshell: Oliver Sacks (a humane man & a fine essayist) made up many of the details in his famous case studies, deluding neuroscientists, psychologists, & general readers for decades. The man who mistook his wife for a hat? The autistic twins who generated multi-digit prime numbers? The institutionalized, paralyzed man who tapped out allusions to Rilke? Made up to embellish the stories. Probably also: the aphasic patients who detected lies better than neurologically intact people, including Ronald Reagan's insincerity. https://t.co/77nQRF8kp6

[David Fowler @davidfowl]

I'm now convinced there should be an entire university course on how to work in an existing code base (notice I didn't use the word legacy). The end goal being to make a change to it without breaking the functionality. This would be a senior course. CS401 Software Refactoring.

[Markus Deserno @MarkusDeserno]

May I invite you to a fun thread about a delightful quirk of relativity theory? Starting with a simple fact about rotations, I’ll hope to give you some intuition about something that’s considered wildly counterintuitive: velocity addition. Intrigued? Buckle up!

[Corey Quinn @QuinnyPig]

Since a lot of friends seem to be getting MacBooks Pro, I will dump some of the things I do to set mine up as a former Grumpy *nix Admin(tm).

A thread...

[eric carle @ericcarle]

Happy Very Hungry Caterpillar Day on the first day of Spring!

[Patrick McKenzie @patio11]

https://t.co/FrNz9OEKhb is tracking availability of the covid-19 vaccines in California. @ca_covid volunteers are calling hospitals/pharmacies to ask if they will administer to 65+ year olds.

We called 100+ Thursday and will do 500+ Friday. 24 sites confirmed; more to come.

[Corey Quinn @QuinnyPig]

@lkanies @luca3m And a great search engine for those docs and calendar events in https://t.co/lt4LyjtKXu but they never EVER talk about it.

[Matthew Sheffield @mattsheffield]

Thread: Meaning and loss in American conservatism

I've written a lot about how Christian supremacism (expressed and implicit) is the underlying objective of most Trump supporters but the psychology of American conservatism is very important in its descent into madness.

[Dr. Danna Young🇺🇸✌🏻 @dannagal]

I've received several DMs from friends asking what do to about parents/family members who believe misinformation regarding the election, vaccines and COVID. Here's a research-based thread to help explain the roots of these beliefs and how to (and how *not* to) address them. 1/

[Kareem Carr, Ph.D. @kareem_carr]

When academic experts like me try to share our knowledge on social media, we attract our own special kinds of reply guys (and gals!).

Here's my list of academic reply guys! 👇

[tobi lutke @tobi]

I can't just passively listen to audiobooks/Podcasts. Walks and drives are perfect. Anyone got any other hacks? Someone suggested playing tetris, or some other game that doesn't use the frontal cortex.

[Noah Smith 🐇🇺🇸🇺🇦🇹🇼 @Noahpinion]

I wanted to understand more about the COVID-19 vaccines and the future of the pandemic.

So I interviewed the great @VirusesImmunity for my blog!

It was hugely informative.

https://t.co/eHZnzpBZCu

[🔎Julia Evans🔍 @b0rk]

I'm almost finished writing a zine about bash, so here's a thread with a few sample pages from the zine

https://t.co/UBeFN23uUW