标签：#car

Building in public You know the risk before you start. Everyone tells you: do not build something the platform could ship. You build it anyway, because you need it and nobody has it. Then one Tuesday the release notes arrive. What the months actually looked like I want to be precise about the cost, because the cost is the reason the release notes hit the way they did. Two hours of sleep on a normal night — not one heroic week, the normal shape of the last few months. Work during the day, build in the evening, debug until the birds started. Weekends were the good days, because nobody interrupted. What got built in that time: a memory layer for AI coding assistants. It saves what was learned after a fix and reads the relevant parts back before the next task. It runs over MCP, so it works in whatever editor you happen to open. It survives restarts, model upgrades and switching tools. I did not build it as a business idea. I built it because I was tired of explaining my own four servers to an assistant every single morning. The hour the release notes landed Anthropic shipped memory into Claude Code. Not "context improvements", not "a longer window". The word in the release notes was memory — the same word I had been using for months to describe the thing I was building. I read it twice. Then I sat there and did the arithmetic that everybody in that position does: months of evenings, the sleep, the weekends — against one line in someone else's changelog. The thought was not complicated. It was three words long. Who needs mine? If you have never had a platform ship your feature, the closest thing I can describe is finding out the thing you have been carrying uphill was already at the top. Not that it was wrong. That it was unnecessary. I did not open the editor that evening. That is the honest version. I read the docs, I read them again, and I went to bed early for the first time in months, which is a strange way for a bad day to end. Why the fear was rational, not dramat

I founded Krasyn, an outpatient EMR with an AI scribe inside it. Krasyn has run a working outpatient clinic's real patient records since March 2026, so what our scribe drafts ends up in charts that real clinicians sign. This post covers two things we shipped in August: a published benchmark of how faithful those drafts are to the transcript, and Note Check, a tool that reads any scribe's note against its transcript and lists what the transcript does not support. Why a fluent note is the problem A faithful note and a note with one invented blood pressure look the same on the screen, and the clinician who signs it owns every sentence. Published evaluations put ambient-scribe hallucination at about 1 to 3 percent of notes. A March 2026 analysis of 71,173 AI-drafted and finalized note sections found a confirmed edit in 5.8 percent of them. The drafting got automated. The checking did not. I wanted a number for our own scribe that I could defend, with the definitions printed next to it. A benchmark without definitions is marketing. The unit: a clinical assertion We measure at the level of a clinical assertion, one atomic statement about the patient that could be true or false on its own. "Denies fever, chills, and nausea" is three assertions. A measurement and its value are one. Hedging is kept verbatim. Every assertion gets exactly one label against the transcript: Supported: the transcript says it, or it is a faithful paraphrase or clinical translation. Inferred: not stated, but a reasonable clinical inference with a basis in the transcript. Tracked separately because it is the contested category. Unsupported: no basis in the transcript at all. Contradicted: the transcript says the opposite, including a symptom the patient denied, a treatment the clinician declined, or another person's symptom attributed to the patient. Hallucination rate is unsupported plus contradicted over all assertions. Coverage is measured separately against key facts per case, because a note tha

Chinese safety regulators have cracked down on doors that don't open in a crash.

Alphabet-owned company is seeking to persuade US regulators to clear a path for fully autonomous taxi services.

Tesla has discontinued Solar Roof, its solar panels designed to look like regular roofing tiles, Electrek reports. Sources "close to the program" told the publication that Tesla has informed its third-party installer network that Solar Roof is no longer available to order, and that only conventional solar panels will be supplied going forward. While Tesla […]

The UK government is facing calls to cancel a sprawling health care contract with Palantir. The region of Greater Manchester insists it can do a better job itself.

Classic Machine Learning Through the Eyes of an SRE — Part 7 Picture a client health metric that has been flat at 2 out of 10 for six months. Ask PCA to compress your client-health data and that metric will contribute almost nothing to the directions PCA decides to keep. Not because PCA is broken. Because PCA treats variance as importance, and a signal that barely moves contributes almost no variance. Reduce the data far enough and the independent information it carried is simply not there anymore. But a CSAT frozen at 2/10 is not noise. It is a crisis nobody is escalating. And after compression, it may no longer be available to anything downstream. That is the bet, and in ops data it is frequently wrong. The critical signals are often the quiet ones. There is a cheaper version of the same failure that catches most people first. PCA measures variance in whatever units your features happen to be in, so a metric ranging from 0 to 10,000 can dominate one ranging from 1 to 5 purely because it is bigger. Standardize before you compress, or your first principal component may just be an elaborate way of saying "ticket count." Same class of bug as unscaled features in K-Means and SVM, and it fails just as quietly. What PCA actually is Third answer-finding strategy in the unsupervised set, using the same shorthand as the last two articles. K-Means SEARCHES: iterate and hope. DBSCAN DEFINES: declare a rule and traverse. PCA SOLVES: an eigendecomposition or SVD gives a direct solution rather than an iterative local search. No convergence to babysit, no restarts, no local optima to escape. Two caveats on the word "direct," both worth knowing. Many libraries will use randomized SVD on large matrices, which is approximate and stochastic. And even with an exact solver, eigenvectors are only defined up to sign, so a component can come back inverted between runs or across implementations. The variance explained is identical either way, which is precisely why nobody notices. Hold ont

Genesis, Hyundai's luxury brand, just revealed its first full-size, three-row electric SUV for the US market, the GV90. And arguably it has some of the wildest designs and features in the auto market today. Right off the bat, the coach-style doors signal that things aren't what they seem with the GV90. When the front and […]

A retractable screen, a huge heads-up display, and an optional 4-seat VIP interior.

Seven months after Elon Musk announced that Tesla Robotaxis in Austin were operating without human safety monitors onboard, the city's service appears to have finally gone fully driverless. Over the past two weeks, all 170 Tesla Robotaxi rides in Austin monitored by the crowdsourced Robotaxi Tracker were unsupervised, the site's creator, Ethan McKanna, told The […]

Last year, Audi announced that it gave its all-EV-by-2033 plan the boot, and instead will offer a mix of gasoline, hybrid, and electrified propulsion. There's no doubt still some uncertainty among bigger automakers - especially those under the Volkswagen Group umbrella - when it comes to such a (now prior) commitment. Even so, what it's […]

A usage policy for Flock license plate reader cameras tells police not to talk about the cameras: When cops use Flock to arrest someone in Wapello County, Iowa, they don’t want them to know. A usage policy for the automated license plate reader cameras in the county tells police, in no uncertain terms, to keep them a secret: “DO NOT MENTION ALPR USAGE TO THE OCCUPANTS OF THE VEHICLE,” the policy document reads. “DO NOT MENTION ALPR USAGE IN YOUR REPORT OR COMPLAINT UNLESS ABSOLUTELY NECESSARY.” This reminds me of IMSI-catchers (Stingray was the most popular) a couple of decades ago. Police would go to even more extremes to hide their usage...

The cyberattack at CareCloud resulted in one of the largest reported data breaches in the U.S. healthcare industry this year.

The car world is filled with designers still obsessed with shoehorning sex into their rides. Slate went a different route, and it’s why people are smitten with the charming electric pickup.

Preparing for a Python developer interview often starts with coding problems. You practice arrays, strings, dictionaries, functions, and algorithms. Then you solve a few more problems and feel like you're ready. But an actual Python developer interview can test much more than whether you can write working code. You may need to explain your decisions, debug an unfamiliar piece of code, discuss Python concepts, or describe how you would approach a real development problem. Here are the areas I'd focus on before an interview. 1.Don't Just Solve Python Problems—Explain Them It's possible to solve a coding problem correctly and still struggle in an interview. Interviewers often want to know: Why did you choose this approach? What is the time complexity? What happens with edge cases? Is there another way to solve it ? How would you improve the solution? Try explaining your solution aloud after solving it. If you can't explain why your code works, you probably don't understand the solution as well as you think. 2. Know Python Beyond the Basics Don't stop at syntax. Review concepts such as: Lists, tuples, sets, and dictionaries Mutable vs immutable objects *args and **kwargs Exception handling Iterators and generators Decorators List comprehensions Context managers Object-oriented programming Memory management You don't need to memorize every Python feature. Focus on understanding concepts well enough to explain when and why you'd use them. 3. Practice Debugging Real developers don't spend all day writing code from scratch. A large part of the job involves understanding existing code and fixing problems. Take a small Python program with a bug and practice: Reproducing the problem. Reading the error carefully. Finding the likely cause. Testing your assumption. Fixing the issue. Explaining why it happened. This is also useful interview practice because debugging reveals how you think when the answer isn't immediately obvious. 4.Be Ready for Real-World Questions Depending on t

Can't believe I spent 2 weeks writing this. Last week, I gave a talk at a Cursor community event...

US healthcare is broken. Under RFK Jr., the research agency working to fix it is, too.

Within minutes of this post going live, this laptop goes back to the company. Work is handed over....

The Tesla Cybercab, that golden two-seater central to Elon Musk's robo-supremacist ambitions, is finally nearing it's public launch. Whether or not the no-steering wheel and no-pedal vehicle is actually ready for public roads, let alone customers, remains very much in doubt. According to The Information, Tesla is planning a public launch of the Cybercab in […]

The American automaker returns to the top category of endurance racing next year.