nathants

how are bite sized models going to solve bad writing?

coding agents, co-agents, and coco-agents.

Just exchange json.

Backend in python/ruby/go/rust.

Frontend in javascript/typescript.

Scripts in bash/zsh/nushell.

One upon a time there was a low amount of friction and boilerplate with this approach, but with Claude and Codex it’s changed from low to none.

400 - 128 = 272. Codex cli source.

Usable input limit has not changed, and remains 400 - 128 = 272. Confirmed by looking for any changes in codex cli source, nope.

Location: USA Remote

Remote: Yes

Relocate: For better remote timezone

Tech: All

Resume: https://nathants.com

Email: [email protected]

TTL=1day

Just have SES put the email in s3, then do stuff.

Interesting. I'm not trying to restore bootable systems, just data. Still, probably worthwhile to rebuild in Go soon.

Definitely similar.

Git LFS is 50k loc, this is 891 loc. There are other differences, but that is the main one.

I don't want a sophisticated backup system. I want one so simple that it disappears into the background.

I want to never fear data loss or my ability to restore with broken tools and a new computer while floating on a raft down a river during a thunder storm. This is what we train for.

This is cool. Do you always --link-dest to the last directory, and that traverses links all the way back as far as needed?

Perl still exists?

How do you version your rsync backups?

Depends how big they are. My high value backups go into S3, R2, and a local x3 disk mirror[1].

My low value backups go into a cheap usb hdd from Best Buy.

1. https://github.com/nathants/mirror

Do something simpler. Backups shouldn’t be complex.

This should be simpler still:

https://github.com/nathants/backup

when i read threads like this, it seems no one had actually used o3-high. i’m excited to try 4-opus later.

just as there are low value students, there are low value reviewers. same as it ever was.

not every review is important.

are you trying to evaluate the author for some certification or test? this is contextual to evaluation.

books are great.

hundreds of hours of video of the author writing that book, is strictly more information.

there are only two options: - have more information - have less information

more is better.

you can scrub video with your finger on an iphone. serious review is always high effort, video changes nothing.

the solution is obvious. stop grading the result, and start grading the process.

if you can one-shot an answer to some problem, the problem is not interesting.

the result is necessary, but not sufficient. how did you get there? how did you iterate? what were the twists and turns? what was the pacing? what was the vibe?

no matter if with encyclopedia, google, or ai, the medium is the message. the medium is you interacting with the tools at your disposal.

record that as a video with obs, and submit it along with the result.

for high stakes environments, add facecam and other information sources.

reviewers are scrubbing through video in an editor. evaluating the journey, not the destination.

username checks out.

finally upgraded to aws go sdk v2. took a week, and required reviewing 20k lines of code. i'm on aws to avoid this type of thing, but it was fun anyway.

i removed the shift key from my keyboard years ago. there's no going back.

harsh, but fair. gonna allow it.

maybe it’s time we make some new lore.

> I only cheat in offline games for the most part

solos doesn't solve cheating, but it removes the team dynamics and social meta games that team modes bring. like wondering whether your teammates are cheating, or failing to compete because you can't find a good team.

obviously cheating is cool. we all love to code, to build, and to hack. there should be a place to cheat, even in pvp games.

there should be a league with open cheating. cheaters need a place to game too!

there should be a league with moderate anticheat, like what you see in games today. it kind of works, and stops all but the most motivated cheaters.

there should be a league where cheating is impossible. where one doesn't have to doubt, ever, whether they died to a cheater or a god. this is where kernel level anticheat is not enough, and solos only should be required.

cheating is about validating inputs and outputs. valid screen displaying into human eyes. valid output out of human hands to mouse and keyboard.

if we take a step back, this is very achievable. it's not like doping in the olympics, we don't need bloodwork. we just need a little more information than we get from anticheats today.

this is why solos are better, you can’t blame your teammates.

handcam anticheat when?

kernel anticheat is necessary but not sufficient.

hetzner is $1.5/TB for us and eu.