This was my reading too. Interesting idea, but it took 10 pages of fluff to get to it and I didn't even believe the final idea when we got there. I started off reading the first part and thought he would get to the part where he realized he was managing context wrong. Never got there, instead he thought it was about the shape of the prompt.
With how powerful these companies are and the enormous impact on your real world life them capriciously deciding to cancel your account can have, governments need to step in. Good idea to write to my federal member here to be honest, I think there is some appetite for reigning in abuses of power of these tech monopolies where I live.
Antigravity CLI or the Gemini one? When I tried the latter about 2 months ago it was shockingly bad, though I was a free user. I assume its better if you're a paying customer?
It doesn't appear that there is an Antigravity CLI, so the ladder. I'm using a paid account though.
For the last few months I was using paid versions of CC, Codex and Gemini CLI, and found them more or less equivalent for my uses. I'm just building web apps though.
Yeah lack of peripheral drivers upstream for all the little things on the board, plus (AIUI) ARM doesn't have the same self-describing hardware discovery mechanisms that x86 computers have. Basically, standardisation. They're closer to MCUs in that way, is how I found it (though my knowledge is way out of date now, been years since I was doing embedded)
I've just been doing some reading. The driver situation in Linux is a bit dire.
On the one hand there is no stable driver ABI because that would restrict the ability for Linux to optimize.
On the other hand vendors (like Orange Pi, Samsung, Qualcomm, etc etc) end up maintaining long running and often outdated custom forks of Linux in an effort to hide their driver sources.
My favourite was, Opus 4.6 last night (to be fair peak IST time, late afternoon my time), the first prompt with a small context: jams a copy-pasted function in between a bunch of import statements, doesn't even wire up it's own function and calls it done. Wild, I've not seen failure states like that since old Sonnet 4
I asked Opus 4.6 to help me get GPU stats in btop on nixos. Opus's first approach was to use patchelf to monkey patch the btop binary. I had to redirect it to just look the nix wiki and add `nixpkgs.config.rocmSupport = true;`.
But the approach of modifying a compiled binary for a configuration issue is bizarre.
It does stuff like this all the time. It loves doing this with scripts with sed, so I'm not surprised to hear about it trying to do this with binaries. It's definitely wilder, though
It frequently gets indentation wrong on projects, then tries to write sed/awk scripts. Can't get it right, then write a python script that reformats the whole file on stdout, makes sure the indentation is correct, then writes requests an edit snippet.
And you might be thinking. Well, you should use a code formatter! But I do!
And then you might say, well surely you forgot to mention it in you AGENTS/CLAUDE file. Nope, it's there, multiple times even in different sections because once was apparently not enough.
And lastly, surely if I'm watching this cursed loop unfold and am approving edits manually, like some bogan pleb, I can steer it easily... Well, let me tell ya... I tried stopping it and injecting hints about the formatter, and it stick for a minute before it goes crazy again. Or sometimes it rereads the file and just immediately fucks up the formatting.
I think when this shit happens, it probably uses like 3x more tokens.
For a Rust project, it recently stated analysing binaries in the target as directory a first instinct, instead of looking at the code...
reply