natsucks

What about the vulnerabilities you yourself introduce when using AI? or is the assumption that (1) there will be zero or (2) you won't ever open source so no one will know about them?

hah yeah i tried this out as an exercise and i found it very annoying to keep up. it feels quite unnatural.

Using TUI is also architecturally simpler. I don't want to rely upon third-party mappings of the CLI/MCP to the GUI, which are potentially incomplete or buggy.

yeah why is this news. breaking: we still need models besides llms.

nice find

I've seen takes on X like, "anyone who's coding manually these days is only doing it to be contrarian."

sorry everyone is being mean to you

this is amazing

okay lets do wide spread price controls and wealth taxes it'll be great

I question all the time what dictates the posts I see on the front page every day, and whether or not it's truly based on organic interest. i wish i could say i up/down vote frequently but i do not and i wonder if that's true for most people.

> I’ve been listening to mates whose companies adopted Claude wholesale, only for their AI use to become a double digit percentage of their salary.

sigh...yep. that's us.

Yes my first instinct is to roll my eyes at these efforts but we'll probably all get something better in the end from all the competition.

I saw this too and I'm really confused.

is it the guy in Nebraska from the xkcd comic

Yes AI content, even when correct and insightful, has a feeling of being disposable. Maybe it's because there is no person behind it.

i like this comment.

can we just get Opus 5.1 already

i've noticed recently that some agentic TUIs have introduced a dashboard of sorts for different sessions that you access by just pressing left arrow. i wonder if they are trying to solve some of the problems mentioned by the author and whether that would ultimately be the best solution.

yeah the conflict of interest here is staggering.

everyone is shipping their in house solutions and they all seem...kinda the same.

yeah they were probably thinking, "we really gave away the transformer recipe for free?"

so..you guys have $20k+ rigs?

hah. it's true. no interest in uncertainty except when forced.

very cool. thanks!

I've been wondering what the point of a lot of these new multiplexer projects are when tmux is so extensible. I'd be curious to see eactly what you've done. Care to share a tmux config?

I really appreciated this post. I just turned staff. Putting up my antennae to probe what problems are out there is a skill that I am trying to hone. However I find that I am often blocked in some way that is hard to articulate. Maybe it's because I am on a fully remote team and the silos prevent me from getting enough information. Also a lot of times my antennae pick up the same problems - the problems that are mammoth and above my pay grade and intractable - and I just throw up my hands and go back to what I was doing.

The skill really does seem like an art though. I'm hoping with time I can get over these obstacles.

lol

The question i wonder about is, when will an event come along that persuades everyone that human understanding is still required? Or will it never come?

And what about problems that cannot be one-shotted but helped along?

I am feeling this a lot lately. Getting the most out of agents seems to require being able to ask the right question. And how can you ask the right questions without deep domain expertise?