Rust can only prove a limited subset of correct programs to be safe, when you're doing bare metal stuff you've often not in that subsystem and drop down to unsafe. I'm guessing there's always stuff that's not perf critical and can live in Rust sandbox - so not saying no wins - but it doesn't sound like Rust is a no-brainer.

Every model release now has been straight price increases since what GPT 4 ? When was the last time a new flagship model decreased prices compared to the previous one ?

Then I just iterate with LLM - I let it start writing stuff in YOLO mode and check on what it's doing in the code steering it in the direction I want.

Usually the code LLM generates will work but is kind of garbage - but I can easily steer it towards better implementations.

Sometimes using an LLM is theoretically slower than hand-rolling - if I just sat down and focused I could outperform the iteration and the waiting, especially considering how stupid agents are at running expensive builds/test suites (with a bunch of explicit instructions in skills/claude/agents.md). But the practical improvement of going with LLM is that you have a bunch of thinking traces saved as a part of your iteration proces - it's really easy to get back into flow. This is a huge productivity win for me given how many interruptions I have in my work day. Like so many people like to point out - writing code ends up being less and less of your time as you level up in your career.

AI just changed how I edit code - I still see coworkers (senior developers) failing with Claude/Codex and get stuck when there are trivial solutions if you understand the full problem space. Right now AI is just a productivity tool.

Forcing LLMs to do a shitty job of what a compiler can do deterministically is not a good approach IMO.

It's precisely because I get swamped with all the non-coding work that agentic coding works so well. And in multiple ways.

- it lets you get back in the flow faster (unless you were used to writing out your inner thinking monologues and reasoning to get yourself back to speed when you come back from a meeting).

- it lets you move faster and take on more on your own, meaning less people needed in the team, less communication/syncing/non-coding overhead.

If you're objective about it, AI coding is going to be amazing for individual productivity. It's probably going to fuck us (developers) over with the reduced demand, lower bargaining power, etc. But just on technical merits it's a great productivity tool.

The models are still not better than me at coding and handholding is required, but the speedups are undeniable, and we're long past the threshold of usefulness. So far all the contrarian takes are either shallow/reflexive pushback because people don't like the consequences, or people working in niche stuff where LLMs are not that great yet. But that has been shrinking with almost every release - in my experience.

I know everyone here writes cutting edge algorithms that were never encountered in the training data, their code is hyper optimized realtime bare metal logic that's used in life or death scenarios and LLMs are useless to them - but most of the stuff I do day to day is solve problems that have been solved before, in a slightly different context. LLMs are pretty good at that.

WTF ? Almost always this was "skipping the parts because the deadline was 2 weeks ago". The "I don't feel like it" rationalizations are maybe 20% ? Unless deadlines are rationalizations too ?

One reason I realized recently - when you work it through with an LLM you get full process history linearly serialized, the back and forth, thinking traces, web lookups.

When I need to get back into the task it's much easier to get back in to "the flow".

I think it'll be common practice to start commiting agent logs with the code pretty soon.

Sounds like the basic gist of this

That's a weak criteria - hallucinations are mathematically impossible to eliminate in humans.

Did you ever do any DAW ? Did you have to use is jackd ?

Stuff like streaming games from my desktop in a non native resolution is a no-go with Wayland. I can't do HDMI 4k/120 with HDR/VRR like I can on windows (I know it's HDMI fault, but that doesn't change the fact it doesn't work).

Oh and I've given up on using Linux for productivity a year ago - one can take only so many full browser crashes for simple stuff like desktop sharing, camera/mic stopping mid call.

I'm running linux on my desktop with about as vanilla hardware as you can imagine - the amount of compromises/stuff that just doesn't work is quite annoying.

It's just nowhere near the level of reliability of MacOS - that's why I use my air for productivity and I SSH into the workstation to do actual work in VMs (with all the recent supply chain compromises no way in hell I'm ever doing dev work outside of a sandbox environment).

I've never used a device that claims first party linux support so maybe it's better.

But honestly I'm not a fan of linux desktop in general - flatpack is nice in theory but comes with so many "gotchas" and installing stuff otherwise is just "here you have all the privileges of my user". MacOS sandboxing/security scoping feels way better for desktop use.

With LLMs I just read back a few turns and I'm back in the loop.