i used the bonus anthropic credits to get ornith 1.5 35b q8 running on a jetson. it's no opus 5, but it's usable for real coding and sys admin work, and works great in opencode. at least as good as sonnet 4. 5 token/sec is a little painful though.

https://web.cs.ucdavis.edu/~rogaway/classes/188/materials/th...

Deus Ex is Ultima X, it picked up and relit the torch that Ultima IX dropped in a puddle.

have you read any of OSC's fantasy? i've been meaning to start his Alvin series

You're holding it wrong. Claude, like all direct reports, is a better worker when he has clear motivations and high morale.

it's not clear to me what the interface to the user is, or who the user is

sounds like your goal is to be an embedded systems job shop based on AI instead of engineers? What's your value over existing AI-accelerated job shops that leverage existing quick-turn domestic PCBA suppliers? as a not-so-random example, https://otekengineer.com/

https://www.amtrak.com/superliner-bedroom-suite

He hinted at this when he mentioned that ATC was dealing with other flights complaining about loss of GPS and coordinating with white sands. ATC crew were probably just out of their depth and trying their best, same as the flight crew. I wonder what the experience level of the ATC crew was and how much pressure they were getting from white sands to keep the jamming up.

https://anamnesis.blog/

Struggle alone doesn't do it for me personally, but taking pride in how well I struggle does.

I wonder if Camus had his own answer to that question. Could Camus imagine Sisyphus happy?

I don't think rebellion or ownership are enough. Rebellion is meaningless when you're alone with nothing to rebel against, and ownership is not inherently positive.

Gods not regulating the decent is an interesting take. Can one learn to smile while falling?

Notice that Camus doesn't say HOW to imagine Sisyphus happy. How do you?

I imagine that he's happy because he takes pride in the quality of his work pushing the stone.

your force quitting is probably more from your build pipeline than anything agents are doing.

i use an m2 8gb air with no performance issues at up to 10 parallel claude code interactive sessions (ghostty), each with deep/transient subagent heirarchies that mix claude and codex.

very rarely need to force quit. only seen a couple restart-level failures, and those were on me for being cowboy with subagent delegation logic, resulting in 100s of claude moles popping up faster than i could whack them with force close.

kind of like murderbot and his soap operas

like a compact pickup version of what Edison Motors is doing to the fullsize pickup. i'd take an Edison conversion of an early 90s F250 over any new truck on the market.

https://edisonmotors.ca/trucks/pickup-conversion/

i'd love to see a way (forum, competition, ?) for people to compare harnesses in different domains. folks like accountants, retail store owners, electrical engineers, and all sorts of niches are building personal harnesses/toolkits around claude/codex. those toolkits fit neither their domain communities nor SWE-heavy harness spaces, and a generic home for small niches could help them flourish.

a current problem is nomenclature. i suspect that many people have organically grown toolkits substantial enough to call harnesses, but are not close enough to the SWE bubble to be familiar with the word harness. ai has made it easier than ever to build bridges between domains, but it's also made it easier than ever to get domain tunnel vision and reinvent a super great wheel.

i used custom TRUE/FALSE defines that were maximally-orthogonal-without-being-bitshiftable for a while (0b10011010/0b01100101), but eventually gave in and accepted the 0/1 paradigm the rest of the world uses to avoid friction with every library in existence. the only alternative is to become an ada programmer, and my hair isn't quite grey enough for that.

thoughts on bitflip versus bitshift resilience?