Joe Duncan

@garrytan cumulative graph ragebait :D

GStack still growing every day.

@chrysb @cursor_ai nothing comes close to cursor so far, cc is fully retarded and barely usable with identical setup, models etc

i don't see how @cursor_ai survives - for $200/mo, you can essentially get unlimited usage on claude / codex that same usage would cost thousands on cursor even if cursor harness is better, the price difference is just wild

@davidsenra never heard of 1-6 🤣🤣

Still climbing:

@rezoundous good and new

If everyone can build, what actually stands out?

@deedydas even within single cos, there is a massive spread between people stuck in 2024 and others being in 2026

I’m not exaggerating, I hear from so many big software cos which don’t use Claude Code/Codex. CTOs are asleep at the wheel. Engineers are typing code by hand. Fixing a bug a day. Like it’s 2024. If youre at these cos, demand change or leave. Now. You’re in for a rude awakening.

@WatcherGuru @MarineTraffic pretty bendy for a strait

JUST IN: Video shows ship traffic in the Strait of Hormuz over the last 24 hours.

Turkish Airlines landing in ZRH on RWY 14

will the future get more predictable if everyone uses the same models, or less predictable?

@mattzcarey it's great bc search and execute can be separated here by human interaction if required

Code Mode is all you need, very excited about this direction for MCP blog.cloudflare.com/code-mode-mcp/

work is becoming a lean back experience

@burkov at least it doesn't estimate in tshirt sizes 😂

It's funny that Claude says something like "This is a major refactor: the first stage will take 2-3 days, the second stage two days, and the third stage about a week" while we both know all three stages will be generated in the next 30 minutes.

@samswoora @witty_genstein i still do this style of interview all the time - the code itself is the least important part - it's more about how candidates approach problems and how unknowns are handled and in the end, if they are bs-ing their life or not. i am surprised how many people are dishonest

@witty_genstein Yeah unfortunately humans are slowwww to adapt. Like in a lot of way leetcode was a little obsoleted by Google already, but people kept doing it

This went so bad lol. First time in my life I felt like I was being punished for not cheating. They did no google since google has the LLM top-line. forgot some syntax thing and just wasn’t prepared since I’ve been so busy with baby. He ended with “i had so much fun talking” LOL

@cremieuxrecueil a lot of them are configured to go off at random as well (at least at airports)

Metal detectors don't really seem to detect metal, or even the same things each time you go through them. Depending on the day they just like or dislike what I'm wearing.

ban all beeping household appliances

@heyrobinai still too slow and robotic

no way this isn't killing call centers PolyAI just got Marriott, Caesar's Palace, and Gordon Ramsay's restaurants to fire their phone staff.. this AI handles every call and you literally can't tell it's not human here's how it works:

Now that we've launched Zipping Points, we can pick up packages and deliver autonomously from literally any location. Here's a Zip grabbing a package from one of our restaurant partners. Will take so many cars off the road over the coming years!

Weird that it feels way more natural whispering to ai Whisper = talking to AI Normal = talking to people

@karpathy taste

Has anyone encountered a good definition of “slop”. In a quantitative, measurable sense. My brain has an intuitive “slop index” I can ~reliably estimate, but I’m not sure how to define it. I have some bad ideas that involve the use of LLM miniseries and thinking token budgets.

@ryanzip if you go even faster you can keep the food warm by friction

Zipline food deliveries 4m8s Competition in cars 19m30s Hot food that arrives hot

you can do it - write that email you've been holding off since last week.