deet

If we are going to privilege privately operated transportation providers like Waymo with special access to streets relative to individually operated vehicles, we need to rethink whether a private company's terms of service should govern the rights and privileges of users of such services or if users should have more substantial protections.

Waymo has chosen to monitor travelers in a way that drivers of their own cars would not be monitored, while the government has chosen to ban privately owned vehicles from some spaces (like Market Street in San Francisco). This coerces individuals into sacrificing privacy and other rights.

Imagine if your phone company listened to all your calls and reported you to the police if it didn't like something you say.

And what happens when a private company like Waymo partners with a municipality to integrate into its transportation network? Is that now privately operated vehicle or part of a public space system like a sidewalk or the road itself?

Waymo is not like mass transit or even a taxi: only one group of passengers are in the vehicle at a time. Subway and bus rules don't cleanly apply. It's closer to a rental car that drives itself.

We as a society are turning to rely on or even require private companies for much of our essential infrastructure and interpersonal fabric: communications, payments (decline of cash) transportation, surveillance (Flock), places of congregation (virtual town squares), etc. Meanwhile because they are private they are not bound to privacy and other protections like the state itself.

We should rethink this direction.

Yes, perhaps fair. But my point was somewhat narrow. I wasn't saying that team-managed agents are good to go for all cases and that they're better than individual dev-managed ones. Just that they have gotten better and that of those Devin has some of the better UX.

Our experience might also not be typical because we have built infrastructure around making Devin and similar agents work better. And for the record no ties to Devin/Cognition. Just pay them too much as a customer.

As others have mentioned, it's really matured a lot and at this point is one of the best cloud-hosted, team-managed coding agents, when factoring overall UX, testing and QA lifecycle via its sandboxes, and its ability to be controlled with an API. We use it quite heavily.

It's coming from a different starting place than Claude Code or Codex are as individually controlled single-developer tools. Devin has been more persistent in pursuing the direction of something that operates more autonomously at the team level, as a peer. And while it might be slightly behind in raw harness ability (maybe?) it's probably ahead on the team-focus.

"Let us cultivate our own garden." - Candide

The key is consciously making that choice. What people don't want is to be forced into a way of living by others. People can accept what they have a hand in discovering and choosing.

Imagine if you couldn't buy a lathe unless it refused to make a baseball bat (which could be used for hitting people).

Or if you couldn't buy scissors (because they could cut brake lines).

Or if you couldn't buy a car (because it could be used to run someone over).

And if all of those checked with the government before functioning.

It's almost like maybe instead you should just ban the undesirable end action, enforce that law, and create societal conditions that don't nudge or force people into doing undesirable things.

While commuting can be chaotic, I don't think what you're calling out is the central point of the article.

Spaces that are less chaotic - coffee shops, gyms, even elevators - are places that people used to be able to strike up random short conversations with each other. Sometimes these would become longer. Sometimes they even turned into friendships.

It still happens of course, but I, like the author, am saddened that casual socialization seems to be on the decline.

I like to say Hi to people in elevators. Some reciprocate. Some find it awkward. But I don't even bother saying Hi to those wearing AirPods since that would be rude, interrupting them. Could an interaction have brightened our mutual days? Could we have become friends? Who knows, AirPods preempted it from the start.

We've found that methods like this substantially increase the quality and reliability of coding agent output. The ability to run code in a sandbox, drive an interactive session using a browser or API calls or other apps, and visually confirm output via vision models all adds up to plugging a big hole in the feedback loop for agent modifying a complex codebase.

We've had agents go as far as interactively testing how our product responds in video calls by launching our full stack in a set of docker containers (app, api, db, queues, etc.), all inside a larger sandbox, populating test data, connecting the mock system to a real video call solution like Google meet, and injecting audio and video to test the response. End-to-end, like a real user flow.

It's not perfect yet, but if you are a skeptic on the ability for AI agents to productively modify a complex product, I'd highly encourage you to play with a setup like this before ossifying your conclusions.

To be fair though, models might be changing the calculus for what constitutes a vulnerability that is too small / too obscure to care about.

If AI is reducing the cost of using the long tail of small vulnerabilities or is making possible chaining them together into something more profound, then those small, less-concerning issues might requiring addressing in a way that was previously not required.