In our case, we wanted to borrow the UX of email (to be intuitive to knowledge workers) but not necessarily the implementation.
Full control of your data was a design principle from the beginning, including being able to run fully offline with local models, so we didn’t want to add a dependency on email.
With that said, you can certainly hook up an MCP server and have the agents read and send emails (with human-in-the-loop approval) on your behalf.
>This is why we’re releasing Pion today. Pion is available as a research preview. If you have an existing business or an interesting business idea you want to hand off to AI, please sign up on our waitlist to get access. We’re excited to run many more businesses, and through them, contribute significantly more insights on frontier model capabilities.
> "The paste operation might fail silently," according to Microsoft.
> Excel 2016, 2019, 2021, and 2024 are affected. Microsoft said: "Although users try to paste content, the source remains selected and the destination is unmodified. When this issue occurs, users receive no indication of the failure, such as a beep or error message."
> Related tools, including Microsoft Management Console (MMC), RDS Licensing Diagnoser, and File Explorer might also become unresponsive," Microsoft admitted.
> "Additionally, the Windows Update page might stop responding and continuously display a loading indicator."
This culture of trying to avoid showing the user an error message has to stop.
I remember the time when spurious copy-paste failures meant something shit the bed so badly in the Win32 subsystem you needed to reboot. Never did figure out why that would happen but it kinda stopped around the Windows 8 era...
the fact that you have to encourage these models and tell them that they can solve these problems and warm up on easier problems seems to indicate that there's something to AI pairing above and beyond prompt
They are relying on training data of humans talking about how hard these problems are. Same way an un-reminded Claude gives estimates for work that are as if a human is doing it by hand, but then will drop them by 20x if you remind them it’s going to do the work.
I would think this type of behavior (ugh, or dare I say default mindset) by consumer-facing LLMs will always be desirable for ‘hard’ problems (things previously unsolved) because it’s a bit like having saftey mechanisms in place to prevent hallucinations for users incapable of verifying correctness of the output. You’ve got to do a little work to prove you understand that it’s hard but it’s still something the LLM might be able to accomplish.
I think this is also a healthy mindset for a person to have in many cases. If my boss asks me "go solve P = NP", as extreme example, I would also give some pushback.
I spent about a month walking through proving something with Claude a few months ago and it _constantly_ told me that it was impossible and I should stop working on it, right up until it proved it.
It will likely burn a lot of tokens, take a long time, and might not work, so hopefully they'll still ask if you really want to spend the money on the attempt.
One way they improved the hallucination problem was basically training the models to refuse to do or say something if they are not very sure they can do it. As a side effect, they refuse to work on problems they know are extremely hard.
reply