jesse_ash

It's very useful, and actually kind of critical for the way I find code reviews valuable. If the person hasn't reviewed their (agent's) code before I get to see it, then I'm not really talking to that person about their architectural or design ideas, they're just the 'meat proxy'. The agent isn't going to develop deeper opinions about the project and product, and neither is the person if they didn't read the code before review.

It's these kinds conversations and constructive challenging of ideas that I worry for the most when orgs talk about reducing code review bottleneck.

At another level, code reviews also give you the time to really think about what is being built and why. I've often come across looming architectural or strategic failures simply by having to stare at a bunch of code and wonder why it works a certain way. Same goes for writing the code by hand too, though it's harder to see past your own biases and ideas sometimes. I find code reviews deeply valuable for myself and my team.

Yes shocking.

Hah! I also thought about it this way and ended up added a "purple elephant rule" to my pi prompt to discourage the behaviour, since I figured LLMs lean on metaphors so much.

Of course, I quickly reverted this change as purple elephants started cropping up in comments and other prose :)

Even with web projects, the issues of LLM coding tendencies and its lack of product 'taste' or whatever you want to call it are apparent. Janky UX, poor information transmission, bloated modules... it's just easier to sell web-based AI output because it's visual and interactive, and we are easily impressed by bright colours smooth animations.

I won't argue that the web is more 'capturable' by LLMs, though. It was maybe slightly out of reach by a large cohort of developers who wouldn't have considered themselves "UI people" (or who scoffed at it for various reasons), but now is well within vibe-territory.

I like your idea of conversational tempo, it feels a little like a 'thinking' slider applied to a plan mode (how much back and forth vs. "rigor" you want at a given moment).

Might be a good candidate for a pi extension.

Personally, I had to go back to Opus 4.6 after I felt what I thought were some early onset signs of psychosis.

It seems ridiculous to type, that a model could have this effect on my mental health, but my quality of life and enjoyment of work has improved drastically since I stopped subjecting myself to reading this style of output 8 hours a day.

Yes. Every single response has this level of _serious_ detail (the kind you'd only go into when you really need someone to understand something).

> The UI of git directly reflects its internals

Maybe?

Love this idea and will be following closely! I've wanted a pair programmer style interaction for a while now. Something closer to VSCode's Copilot inline conversations and FIM, but where it's continuously watching what I'm doing and ruminating on suggestions.

Those looking for a one sentence answer will be the quickest to invest. When people talk about the harms of AI, this is the kind of thing that comes to mind first for me.

IMO the assumption is probably that, with LLMs generally, software complexity and surface area going up faster than we're tackling it through hardening, testing, etc. - even with the help of defensive models.

I would also imagine bad actors are in the majority, and so we're seeing restrictions on models like Mythos in an attempt to balance the field a bit.

It was a bit misleading in terms of the audibility of infrasonic noise, but I think he did a good job of highlighting some of the effects of infrasonic noise on QoL/health with the study towards the end. IIRC, he also recorded some regular human-range noise that I would personally find disruptive to have to live with (though this was a fair bit closer to the data center than the claimed range of infrasonic noise's effects)