if you actually figure out enough pieces of bugs, even opus level model would be able to chain it together imo, and the latest china models has already been described as close to such level.
I guess some Tesla are manufactured in China lol. I am just trying to say that the liability that Chinese manufacturers takes aren't more than the US ones.
I think Google added that AI-generated responses maybe incorrect? When you are paying such a low amount of cost, like probably for free, I don't think you can expect a same level of quality as a human written or reviewed of answer. It is like same random user spin up their Lovable and vibe-coded a piece of slop and hold Lovable responsible for not giving them production quality code. It is simple, you get what you paid for. If someone actually figured out AI that is actually always correct, it would be charged in superhuman price as well.
That's not exactly the case in China, the current state of FSD is still pretty dumb, unless you consider transferring control back to the user at the very last minute before it crashes a proper way to handle risks.
notifytun local --target [same-target-you-use-for-ssh]
Now you get Desktop notifications on Mac/Linux/Windows when your coding harness needs your attention. Same SSH connection you already using, auto-replay on reconnections, it just works.
---
I personally has an isolated VM to run Claude Codex/Codex on full auto so that I can leave it around and do something else, need a way to get notified when it is done, so I built this.
No port forwarding or sending your notifications to some random server, just the same SSH connection you already using, if you can SSH into the box, you can get notifications from it. Hooks setup is fully automatic. When you disconnects, notifications goes to a sqlite store on the remote box, so that it can be replayed when you reconnect (won't flood, just give you a summary if there are too many notifications).
In that case I think you can have a refund subagent that is responsible for checking if the user really asked for refund before doing these dangerous things. But it only minimize errors, LLMs are non-determinitic by nature.
Just sent an connection invitation on Linkedin. This is actually designed for allow e2e automation using playwright-mcp for a previous startup i worked in that does voice-based job interview agents. The http endpoints is provided by a daemom sitting on the background, listening all input to the virtual mic and transcribing and storing it. The agent can hit /speak and /transcript through an mcp. We have built Livekit Agents specific solutions by injecting text responses but felt that is not enough since we want to be able to test the whole thing end to end so I hacked a way to do virtual mic/speaker. It was designed for closing the dev-test-debug loop so that Claude Code can develop on its own rather than relying on human to test it.
Interesting, I have built https://github.com/michaellee8/voice-agent-devkit-mcp exactly for this, launch a chromium instance with virtual devices powered by Pulsewire and then hook it up with tts and stt so that playwright can finally have mouth and ears. Any chance we can talk?
I only run software from Chinese companies inside a sandbox, either on my Android/iOS phone or inside a VM for desktop apps and only enable necessary permissions. Unfortunately Mainland tech giants have no sense of user privacy and would like to maximize their profit by collecting every single bit of your data because they don't profit on selling you the software, they profit on selling your data.
In that case we should have some sort of UI test backends I guess? This mcp was more for generic use cases which will allow any TUI framework in any language to work.
i think cs students should force themselves to learn the real thing and write the code themselves, at least for their assignments. i have seen that a lot of recent cs grads that has gpt in most of their cs life basically cannot write proper code, with or without ai.
I bet aoftware that is so secure to be compared to products of other engineering fields does exist (e.g. avionic systems), but you will have to pay a much higher cost to use it, luke hundreds of thousands dollars since the cost of acheieved the guaranteed security level would also be much higher. Given the low cost of modern consumer software, you really have to understand that you get what you paid for. And if you want security guarantees you don't just need that particular piece of software being secure, you need qualified people to operate it, the hardware running it being secure (probably propietry and cost hundreds of thousands), and the whole software stack being secure as well, from firmware to OS to networking code. This is simply not somehow that your general consumer can afford, and if you enforce that level of security in consumer software like smartphones, it is safe to bet that almost everyone that has a smartphone would be protesting since they would have no Software aviliable on there phone anymore.
Like one comment above said, there do exist ways to enforce that level of software security, (like railway traffic lights) but the cost would be ridiculously high, and those systems are probably not running any consumer kind of software stack, probably without an OS since Linux would has it own vulnerability as well. Those systems are probably made for custom hardware that the software vendor has total control of it as well.