JSON x (@putFM) header
JSON x (@putFM) profile picture

Startups, software, gamedev Build startups | AI engineering

Joined May 2013
Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)Photo by JSON x (@putFM)
Replying to @rough__sea
It’s software engineering not software typing
30
225
29
3,450
296,582
“You cannot get a simple system by adding simplicity to a complex system.” — Richard O’Keefe
4
37
4
322
16,932
“We are no longer securing computers—we are securing society.” — Mikko Hyppönen
1
12
62
9,091
u know what DOESNT have any critical vulnerabilities??
2
1
17
611
JSON x retweeted
An 18 year old today will spend almost 20 years on their phone by the time they’re 75
30
14
5
212
6,781
Sometimes a demo is simply to remind the world that your competition has no desire to dream -- and no ability to evolve.
353
1,371
137
21,586
415,049
JSON x retweeted
when you realize you're not being buffeted by the waves you're being buffeted by your reaction to the waves
3
4
37
2,856
Wait a second, why does the AI never choose Java?
462
118
82
6,571
903,668
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
185
150
65
3,190
359,114
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.
1,710
6,772
1,587
56,891
8,248,467
JSON x retweeted
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.
1
2
6
700
JSON x retweeted
founders finding out building a startup is 90% sales and marketing:
99
87
31
1,350
45,081
The Innovator’s Dilemma explains why. It’s because of their existing customers.
why is Google in last place in the AI race? Can anyone tell me why?
1
1
9
481
JSON x retweeted
Nobody is ready for this scenario
Readers added context they thought people might want to know
518
625
178
13,716
1,662,917
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.
183
184
87
3,537
396,620
JSON x retweeted
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/…
74
244
119
3,398
1,365,395
JSON x retweeted
Luck is literally just a statistical probability. If you increase your sample size, you increase your luck.
91
34
8
457
15,571
Hogwarts Legacy is now on GameToMac Running smoothly on Apple Silicon Which game should I add next?
37
4
107
8,338
JSON x retweeted
Replying to @ProofofMaro
Life's all about wells
1
24
JSON x retweeted
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 😇
253
48
288
1,990
883,870