Building AI for the real world. token maxxing. prev: https://xitter.cf/t.co/qB3Y1eZhnG, martech, enterprise consulting, @Techstars
Columbus, OH
Joined January 2009
- Tweets2K
- Following994
- Followers320
- Likes2K
Winkle retweeted
Just spent the last 7 days on the front lines of the vulnpocalypse fending off an active cyber attack on one of our products.
Some thoughts:
- Software factories are going to be required equipment for everyone. There’s just no way to keep up with the pace of highly automated adversaries without one.
- We were lucky because we had spent the last few months getting our software factory running well. It is nice to have for product development but proved to be absolutely essential this week.
- At the minimum you need to have a coding server in the cloud pre-provisioned with read only access to all your logs and all the services you depend on for observability. With that in place you are a prompt away from reasonably good situational awareness, ongoing monitoring with loops, and ability for coding agents to validate fixes against your actual, observed attack patterns.
- Shared coding server also unlocks multiplayer incident response where everyone can see every session and jump in as needed. Sharing session links that can be forked is much higher bandwidth than re-explaining things.
- You don’t need to be Ramp/Stripe/Uber scale to have a working software factory in the cloud. We are a team of 3. Ours is built with an @opencode server (thanks @thdxr!), a forked version of compound engineering optimized for automated workflows (thanks @kieranklaassen!) and a multiplayer agent in slack that handles crons (we have our own harness but pick your favorite here).
- To get our software factory up and running well, we had to stop all new product development for ~6 weeks and just focus on getting the validation systems working that enabled us to reliably shipping PR without human code review. This felt very painful in the moment but was totally worth the eventual speedup in velocity.
- KYC for @AnthropicAI & @OpenAI cyber programs is now easy and quick (at least for defensive access), but a day felt like a lifetime this week. Submit your app now before you really need it.
- Getting Mythos access unlocked a deeper level of analysis that helped us shift from reactive mitigation to proactive patching. Wish we had done this a few weeks earlier. Get started now!
Winkle retweeted
In May 2025 we tried a simple idea to make Claude Code more useful for our non-technical teammates. We called it Skills.
Turns out folders go a long way. Today Skills joins @AgenticAIFdn. Thank you to everyone who made agents a bit more useful for yourself and others <3
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.
Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.
Here's what that means for you:
Winkle retweeted
So basically, today PHP got two critical bugs that let anyone run code on your server without even logging in, which is bad, and then the details leaked before the patch was even out, which is worse, and it works on WordPress and MediaWiki and Magento and Joomla and Laravel, and Censys says like 1.5 million servers are running a version with no fix, so the NSA was like "take your system offline," and the FBI was like "take your system offline," and CISA and the UK and CERT-EU were all like "take your system offline," and then the Prime Minister of Japan, the actual Prime Minister, posted at 5:55 in the morning telling 48.8 million people to take their system offline, so everyone took their system offline, like the Dutch cybersecurity agency took its own website offline, and the Dutch parliament went offline, and the Port of Rotterdam went offline, and Finland and France and Denmark started pulling government sites, and Wikipedia went down, and Archive.org went down, and Asana and GOG and Something Awful went down, and the University of Vienna's webmail went down for some reason, and that's just PHP. Because GitLab also dropped a CVSS 10.0, which is the highest score they give out, for a bug that's been there since 2014, so that's every self-hosted GitLab for twelve years, and then LiteLLM 1.107.0 got hijacked and shipped a credential stealer and a remote access trojan in every single wheel and the Docker images, including latest, and you didn't even have to import it, just installing it was enough, and it's the second time this year, and then Railway paused every deployment on the entire platform because someone got into the environment variables, so now everyone has to rotate every secret they've ever stored there, and TiDB Cloud said someone was walking around inside with stolen credentials for basically a month and an extortion group says they took 10.6 terabytes, and Zeabur got breached for the second time in two months and is just shutting down, like the whole company, and Node.js patched remote code execution and a TLS bypass, and CISA says Plex is being actively exploited, and someone took over 300 Tor exit relays to steal SSH passwords, and SafePay ransomware has hit over 600 critical infrastructure orgs, and India's biggest bank filed a data loss incident, and Japan has been in an official state of emergency in cyberspace since October 9, which honestly explains the 5:55 AM post. Oh, and eMudhra, a certificate authority that's issued over 60 million certificates, whose entire job is proving websites are who they say they are, was supposed to be using private keys that are random numbers over a hundred digits long, and one of them was 4. Just 4. And the others were like 66 and 237. Anyway, it's Wednesday.
Winkle retweeted
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine.
• Best-in-class fast local coding
• Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
• Built from scratch in under 4 months
Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
Winkle retweeted
well that was fast! last week's workshop from @aiDotEngineer nyc is now on yt
youtu.be/7T-gldvgfpo?si=KFfT…
Winkle retweeted
For a while now, @kirancodes has been excitedly telling everyone at @BasisOrg who would listen about a crazy idea she's been pursuing. Not everyone thought it was possible, but it's starting to work. See basis.ai/blog/ship-your-inte…
TL;DR: The bottleneck in verifying the world's software is shifting from theorem proving to specifications and semantics. We now have a way to verify semantics that can scale across all programming languages.
The basic idea:
To verify that a program is correct, you need the program, a specification you want to prove, and a semantics that defines what programs and specs mean.
Most programming languages (Python, Ruby, Lua…) have no formal semantics, because semantics are painful to write for complex languages.
You can ask an LLM to write a semantics for you, but it'll probably have mistakes.
But (i) programming languages do have interpreters/compilers, which ultimately are compiled down to machine code, and (ii) some instruction sets do have formal semantics. RISC-V has an official formal model.
So, crazy idea:
Step 1: Compile your interpreter (e.g. Python's) down to RISC-V. Now its behaviour is formally defined. It's exact, but unreadable: thousands of machine instructions.
Step 2: Ask your LLM to write a semantics for your language.
Step 3: Ask the LLM to prove, in @leanprover, that its semantics agrees with the compiled interpreter on every possible program. If the semantics is wrong, the proof gets stuck, and the LLM goes back to fix it.
Step 4: If the proof goes through, you have a semantics you don't need to trust, and you can verify programs in a language that never had one, with guarantees that reach the binary that actually runs.
Kiran has now done this end to end for a simple WHILE language, and we're scaling it up to Lua and OCaml, with Python as the north star.
Winkle retweeted
For your weekend reading: Build with Pi Durable on Cloudflare, a walkthrough of how to create a multiplayer chat agent, including subagents, on Durable Objects.
earendil.com/posts/pi-durabl…
Winkle retweeted
i went from "let me replace hermes and grok bot just for myself" to not only replacing them.. but replacing our family chat too and creating probably the best personal productivity agent
rm -rf hermes grok-bot
meet Pip :)
Winkle retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
Winkle retweeted
My dear friends, I’d like to show you my latest toy project
Introducing Handwired: turn your regular JavaScript code into a neural net!
- no training
- exact outputs vs the JS program
- fully differentiable
All runnable in a browser, without GPU
Winkle retweeted
New on our Engineering blog: Creating in-house source control.
In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale.
Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
Winkle retweeted
I’ve had a few people write to ask me to follow up on a (reply!) tweet I wrote that’s gotten a lot of retweets. I considered deleting it just to avoid the headache, but I think that would make people more paranoid. So let me share my thoughts.
Remember when the web used http everywhere and none of the connections were secure?
And then letsencrypt.org came along and the web was safer and more secure.
Looks like we are back in the http days if we can't rely on the encryption.
EP 53: 2,000 AI Pull Requests: What’s Left of the Code Moat? xitter.cf/i/broadcasts/1mxPaZYqe…
Winkle retweeted
Pleased to announce my first @AntithesisHQ project: a property testing webinar!
In property testing, instead of checking "this input to the function has this output", we check "given a million random inputs, all the outputs have this property". PBT has been around for a quarter century now and is fairly well known in functional programming and distributed system circles.
Which is why we're gonna do something very experimental and target a community that almost never uses PBT: web developers.
See, there's a thousand PBT tutorials out there, and they all use examples like "reversing a list twice returns the original list" and "add(x, y) should return the same result as add(y, x)". These are stateless properties on the code's functions, where we randomize inputs to a fixed test sequence. People have a hard time finding useful stateless properties in their systems.
I've come to believe that most intuitive and useful business properties are instead stateful properties on what must always hold about the system's states. For example, "our total spend is always below our budget cap", or "two talks must never be scheduled for the same room and time", or "free users can't access premium features". We can property test these by randomizing the test sequence itself, to simulate a user doing whatever the heck they want, and testing that no matter what they do, our properties still hold.
So, if you've ever had your data model get corrupted because you forgot to validate one update method, or seen a 500 when the user clicks `send` three times in a row, or gotten mad at SQL for not enforcing cross-table constraints, this webinar is for you.
We'll be live on October 29. Sign up here: pages.antithesis.com/webinar…
Winkle retweeted
to know where you are going, you have to know where you have been:
pldb.kirancodes.me
Titles and abstracts of 22,324 programming languages papers, from the first POPL in 1973 to this year's proceedings.
ALT Webpage of pldb.kirancodes.me
