Tilo Mitra retweeted
I don't see the point to review AI generated code anymore.
AI agents are the new compiler.
We don't review bytecode. We just trust the output of the compiler.
I don't think we should treat AI output differently.
However, the authoring layer cannot be markdown. I feel like there's a paradigm just around the corner that we have missed so far. Maybe a new "language", which won't look like a programming language at all.
Tilo Mitra retweeted
Tesla just confirmed it will end Cybertruck production in 2027. I think it's one of the best case studies we have on managing customer expectations.
Tesla received more than 1 million reservations for the Cybertruck. Our best estimate puts the real number closer to 2 million. That's demand most automakers can only dream of.
Tesla delivered about 70,000 trucks in three years.
You can point to a lot of factors: the design, the production ramp, quality issues, the brand's politics, competition. They all played a role. But they're small compared to the main one.
Tesla promised a $40,000 truck with up to 500 miles of range. It delivered an $80,000 truck with about 300 miles of range.
Those 1 million+ people didn't reserve the truck Tesla ended up building. They reserved a promise. When the product showed up at twice the price with 40% less range, most of them simply walked away. And you can't blame them.
The lesson applies well beyond EVs: the expectations you set become the bar you're judged against. Overpromising can get you a huge order book, but it only turns into revenue if you deliver. Otherwise, you've just built a list of disappointed customers.
Under-promise and over-deliver isn't a cliché. Tesla's Cybertruck is what happens when you do the opposite.
Tesla to end Cybertruck production as sales stall at ~10% of plan electrek.co/2026/11/06/tesla… by @fredlambert
Tilo Mitra retweeted
In a weird way, everybody is rooting for you. When you go to a job interview, the interviewer wants you to be amazing so they don’t have to look anymore. when you go on a date, the person wants to have an amazing date with you. If you make a piece of content, people want to see amazing pieces of content and they have no problem if it’s yours.
the instant you get into the mindset that people want you to do well, your entire world gets better. And you’ll be shocked to know this pattern keeps repeating in different areas of life.
This is like half the internet.
Effective Immediately, all organizations using PHP for their systems are advised to be prepared for an update addressing two critical vulnerabilities. PHP is widely used for web applications. These vulnerabilities often provide a direct path to the server's file system or database. If an immediate update is not feasible, it is recommend that organizations take the system offline until it can be fully mitigated. NSA will follow up shortly with more specific guidance.
1
88
Tilo Mitra retweeted
Give your agent a way to verify its work. This can dramatically improve the quality of output.
With this process in place, Claude Code was able to write 90%+ of its code itself. When generating software at a faster rate than you can review it, the bottleneck shifts to proving that it works. @bcherny and team invested enough in verification, we've been able to move fast while maintaining stability.
Code reviews aren't going away, but you need to think of it differently. One human reading through line-by-line is no longer going to work as a gate, it needs to evolve into a multi-layered verification system, built with fast deterministic feedback loops for your agents.
This is where e2e tests, feature maps (as @poteto has been advocating), property tests and multi-agent adversarial reviews come in. These all provide opportunities to catch errors early and fix them before things get out of hand.
You don't have enough eyeballs for the amount of code being written so your focus needs to be on product intent, risk assessment and evaluating evidence rather than reviewing code. Delegate the code checking work to your automated tests, scale your approvals based on risk, and turn your test failures into living evaluations. This approach helps maintain speed without losing reliability.
Let the agents do what they do best and let you focus on what makes you irreplaceable: judgement, direction, and ownership. We tried to capture how we handle code review and verification in this writeup. Hopefully it's helpful.
Claude writes about 90% of Claude Code's code.
From June to September, merged PRs more than doubled while the share reverted fell by more than 40%.
We wrote about how we changed code review to get there, and how to adopt it:
claude.dev/blog/solving-code…
Yes!
We’re bringing the magic of Waymo to Toronto! 🇨🇦
In the coming days, you’ll begin seeing Waymo’s all-electric vehicles driving through Toronto’s streets as we lay the groundwork for our ride-hailing service.
Our goal is to begin serving riders in 2028.
Sign up for future updates: waymo.com/waymo-in-canada
1
67
Tilo Mitra retweeted
Football is hard to love right now.
You wait 3 weeks for it to return, only to watch your side succumb due to a combination of injuries sustained on international duty, an inept refereeing performance and ultimately lose against a team that shouldn’t even be allowed to play.
Tilo Mitra retweeted
GPT-6 and Intelligent UI, now rolling out in ChatGPT for everyone.
Intelligent UI in ChatGPT delivers fast, interactive answers that make everyday questions more visual, complex topics easier to grasp, and interactive tools for your task available on the spot.
Haiku 5.5 matches GPT 6 Luna on pricing but is more capable and much faster. Let’s keep pacing the frontier.
41
Wtf this is nuts
I'm open sourcing Leviathan: an indexer that lets AI agents search a database of any size without reading it.
At 1M records it hands your agent 436 tokens instead of 107,000, and it finds the answer 99% of the time.
github.com/elstongun/leviath…
70
There’s too much progress happening everyday to keep up.
From concept to reality.
@SpaceX has successfully deployed Starlink V3 satellites into Earth’s orbit and made contact with them for the first time.
At scale, one Starship carries 60 V3 satellites, the same network capacity as about 20 Falcon 9 launches.
71
