JSON x retweeted
“You cannot get a simple system by adding simplicity to a complex system.” — Richard O’Keefe
JSON x retweeted
An 18 year old today will spend almost 20 years on their phone by the time they’re 75
JSON x retweeted
Sometimes a demo is simply to remind the world that your competition has no desire to dream -- and no ability to evolve.
JSON x retweeted
when you realize you're not being buffeted by the waves
you're being buffeted by your reaction to the waves
JSON x retweeted
DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification (carcinization, technically 🦀) for a while.
One of the first projects we migrated was Turborepo, from Go to Rust¹. The migration completed, but the RoI was actually quite controversial internally.
While Rust was in our eyes better for low-level OS access, something crucial for a build system like Turbo, the human migration costs were very sustantive.
Go is very fast. It's beautifully designed. It's easy to iterate on. We were very conflicted about the migration, because it was *humans* writing the code, *even if we knew Rust was a better choice*.
The calculus has now changed. What's "best for humans" is no longer necessarily "best for business".
FWIW, it's also quite unlikely that Rust is the end-all-be-all toolchain. I'm quite certain there's greener pasture ahead, because Rust itself was designed before the 'supersonic tsunami' of agents hit.
¹ https://vercel.com/blog/how-turborepo-is-porting-from-go-to-rust
JSON x retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
Replying to @xah_lee
Around 65-70% of security vulnerabilities in large C/C++ codebases stem from memory handling issues (buffer overflows, use-after-free, etc.).
Microsoft has reported ~70% of its CVEs as memory safety problems for over a decade. Chromium finds the same for serious bugs. Android dropped from 76% to 24% by shifting new code to safer languages like Rust.
JSON x retweeted
I asked Opus 5.5 to make a game inspired by the discovery of the first computer, the Antikythera mechanism.
Everything you see and hear is procedurally generated in real time, from code by Opus 5.5.
It's a single 3 MB HTML file. Playable Claude artifact below.
We asked ten Claude Opus 5.5 agents to devise a faster shortest-path algorithm and prove it in Lean. Within 15 hours, they produced C-HD: a formally verified improvement over the published bounds.
Readers added context they thought people might want to know
C-HD's formally verified bound improves priors only in a narrow sparse density range (m ≤ n⌊⌊log₂ n⌋^{3/4}⌋) as an asymptotic guarantee with enormous constants and no practical speedup demonstrated. vals.ai/blogs/faster-s… github.com/spicylemonade/…
JSON x retweeted
Luck is literally just a statistical probability.
If you increase your sample size, you increase your luck.
JSON x retweeted
Hogwarts Legacy is now on GameToMac
Running smoothly on Apple Silicon
Which game should I add next?
I made $82,221 in August 2026.
⭐️ TrustMRR — $42K
📈 DataFast — $26K
🧑💻 CodeFast — $4K
🐥 Twitter — $4K
⚡️ ShipFast — $3K
🏴☠️ Ship or Die — $2K
🍜 Indie Page — $595
🌱 HabitsGarden — $244
🦐 SuperShrimp — $153
🛡️ ByeDispute — $117
🎞️ YouTube — $112
I didn't work much this month. I travelled to 5 countries and spent time with my family. It's nice to have 6% churn 😇


























