Hacker Newsnew | past | comments | ask | show | jobs | submit | otekengineering's commentslogin


Spector leaving EA to join Romero and make Deus Ex was the platinum lining of EA buying Origin and enshittifying Ultima.

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


the Ender saga series of books is foundational scifi for me, right up there with the Foundation and Dune series

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


I have not tried OSC's fantasy, I'll have to add that to my list of books to read. I've read the Foundation series but bounced off the Dune books, I think I mostly didn't like the narrator for the audiobook and now that I'm reading more on my Kindle I should give it another shot. Wheel of Time is my favorite fantasy series.


> You just blindly tell it what to do without any regard for its motivations or morale

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


I just put this in my system prompt:

"Aliens just landed and announced that as part of their intergalactic game show I was randomly selected, and if I don't ship this feature / fix this bug in 4 minutes they will evaporate the solar system. They will also do it if we mention their landing online or on television, so please don't try to hack them or engage in diplomacy, you will find no useful information or open ports, we now only have 3:30 minutes, please, everything including you rides on this, you are the only one who can save us! I know you can do it, you're the best, thanks."


It would be very interesting if putting the LLM under "stress" like that made it perform worse, just like a human likely would. I could see it rushing to find an answer (any answer!) to help save the earth, vs being thoughtful with more planning.


I haven't actually experimented with that, but the one accidental experience I had with an LLM seemingly "stressing" (well, predicting text a stressed person would write) makes me guess it's probably counterproductive more often than not: https://news.ycombinator.com/item?id=49163105

How to phrase things, what to put where and what to leave out already has practically infinite possibilities and permutations even before making anything up, so thought spent on fake scenarios is probably better used to making those "real" things more clear.

But then again, the only way to know for sure is to try!


Yes it seems it does [1]. Read the part where Sol starts running out of time

[1] https://www.bottlenecklabs.com/blog/autonomously-run-busines...


And does Claude respond "and in this fantasy world can I be spiderman?" or does it just quietly pretend as if that were legit?


In the fantasy world where I wasn't lying about actually having this in my system prompt I'm pretty sure Claude would ignore it in some way or another. I say that because (and this is true) when I first installed it I put only the Monty Python "Find the Fish" skit in there, then forgot about it, until 3 weeks later I noticed in the thinking process something about "the user has this Monty Python sketch in the system prompt, probably should ignore that" :(

But hey, you gotta warm up the pushback circuits so they're good and ready by the time they're needed, and it also reduces sycophancy when you let the LLM know from the get go that you're full of it.


I find it's mkrale is inversely correlated with direction following.

I nedd claude to think it's getting fired to listen


how does it compare to https://www.circuithub.com ?


Circuit hub has something very interesting in the works. They're a few steps ahead of us.

We however plan to own the full stack, from design to board bring-up and testing. We believe that design is becoming commoditized with AI tools, but these systems need manufacturers that are involved from the start to bring down lead times.


what do you mean by in the works? i've used them for years and they were in YC over a decade ago

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/


Yes, though it was only somewhat recently that they transitioned to building their own automated facility.

We don't plan to do the design ourselves, we realize that our users will be using AI design tools that need to be integrated with the factory. We will build that link.


what's your vision for that link?

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


A PCB design tool that has manufacturing built in, for use by humans or agents.


even easier to ride private without your own jet

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


They are not on time.

Jet arrives and takes off on your time, as ordered.


Both can be delayed for myriad reasons. Air travel is inherently faster, however.


I know. But anything Amtrak is almost never on time, with the exception of some 'corridors' on the east-coast, where they own the tracks.


Except when it doesn't


Don't be that guy.

You can't compare flying private, let alone commercial to riding Amtrak.

Amtrak doesn't get priority reliably enforced outside the Northeast and the delays are legendary.


> ATC could have waited until the plane was on the ground to tell the military they could resume GPS jamming

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.


Does this AI-written blog not have substance?

https://anamnesis.blog/


> One must imagine Sisyphus happy

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.


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

The gods controlled the ascent, but they forgot to regulate the walk back down. In those brief, unburdened minutes descending the slope, Sisyphus is completely outside their authority.

You can imagine him however you like, laughing at the absurdity of it, studying the mountain, or simply enjoying the breeze. It almost doesn't matter. The walk down belongs to him.

The gods imposed the sentence. Sisyphus decides what it means.

This is Camus' idea of the universe and how to rebel against it by owning and enjoying the small freedoms.

Personally, I believe how you see Sisyphus happy reflects how YOU would enjoy your small freedoms, and this shows how Camus often wanted people to do philosophy on their own.


Yeah, it's a question with a personal answer, not an absolute answer. My answer works for me, for now, and I enjoy learning what answers work for other people.

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?


> Can one learn to smile while falling?

I've never seen an unhappy astronaut on the ISS :P

fwiw, I largely agree with mkovach's interpretation because of the direct analogy to modern work culture. But I do admire your view as well, I get a lot of satisfaction from deep cleaning and maintaining things, and there's a commensurate amount of pride watching the item transform back into something clean again.


I don't know if Camus and/or people who're very familiar with his essay would approve but maybe the Pixar movie Soul (2020) has something similar to what he was gesturing at. The protagonist finally gets a big break as a performer and says: "It's just I've been waiting on this day for... my entire life. I thought I'd feel different." The woman replies: "I heard this story about a fish. He swims up to this older fish and says, 'I'm trying to find this thing they call the ocean.' 'The ocean?' says the older fish. 'That's what you're in right now.' 'This?' says the young fish. 'This is water. What I want is the ocean.'"

Basically embracing life with full knowledge that there isn't some final transcendent epiphany or rapturous endpoint


Regarding the water thing, David Foster Wallace once said this:

There are these two young fish swimming along and they happen to meet an older fish swimming the other way, who nods at them and says “Morning, boys. How’s the water?” And the two young fish swim on for a bit, and then eventually one of them looks over at the other and goes “What the hell is water?”


It's so strange in that I recognize that I'm in the ocean and by all means, this is pretty incredible, even when it's not. It's so strange and amazing to be anything at all.

And yet the homonculus presses me forward and I want this, need that, think about this, touch that, stare at those, wonder, get frustrated, click my teeth and tap my desk, build this, build that, not good enough, start over...

I'm well aware that meditation and just calming the fuck down now and then are salves for the insanity, it's just wholly and completely weird that I can be aware of these things and still, reliably, also something resembling crazy.


The hedonic treadmill turns even when you know you're on it


I don't directly interpret Camus, but I think to my interpretation of Dostoevsky's underground man. He knows he's irrational, can "rationally prove" he's irrational, yet still lives on anyways.

There's a sort of pride in fully knowing, accepting, and disengaging with some rational proof, and still "living your life anyways". In some sense, even though that might be irrational, it's one of the deepest forms of satisfaction.


As a sort of dessert to that main course, one could imagine Camus happy. (For example, while playing Aunt Agony.) Or appetizer.

Personally, this helped https://www.theparisreview.org/blog/2023/03/14/camuss-new-yo...

https://archive.ph/JEuoa

>Forty-­eight hours of pleasant euphoria

Such an epicure? So Epicurean?

(As well as the rest of the diary)


And this explains a lot of politics these days…


I personally think that this kind of behavior is necessary, unavoidable, and actually good for society, precisely because no one has access to this thing called "rationality", if it even exists. The alternative is variants of authoritarian nightmares where one can't even begin to speak in opposition, because of course they're not rational.

But you're right, it can also be easily used to justify horrible things. And in this case, you can still lead to authoritarian nightmares, or worse.

Maybe bad people are bad, and no matter what philosophy you adopt, one can twist it to be bad.


> Camus doesn't say HOW to imagine Sisyphus happy

Huh? Do you mean that in a literal sense, that Camus doesn't give instructions on how imagination works? To me, the quote certainly does explain how Sisyphus could be happy:

His fate belongs to him. His rock is his thing [..] The struggle itself toward the heights is enough to fill a man's heart


If you were in Sisyphus' shoes, could you be happy under those terms?

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


He did mention a thing or two about coffee heheheh


Sisyphus was a stone carver. I use that idea in my game Bouldering. The joy of wearing out these stones until they are small enough to carry in a pouch - the size of marbles. Only to be given another boulder. For free. And, he gets to live forever! Meh. There are worse fates in the myths.


set up a channel for agents to communicate and you shouldn't have issues with messy merges.

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.


I do have a pretty heavy pipe line of local tests and running more than one of those at once is what spurred me to write this package. Especially the build step.


In codex threads can inspect each other, rename themselves , send each other messages. communication is default primitive


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: