This article is good but it presupposes the norm of democracy and it presupposes (somehow) that the collapse of western democracy will not result in war. Both of these are fundamental misunderstandings, and while I love neither democracy nor war, the dissolution of the American economic system would result in both less democracy and more war.
It’s hard to square this with the post 2024 AI-investment economy. Interest rates have stayed higher longer than expected, while many, many companies (Vercel, Cursor, Wave-whatever that got bought out last year, whatever Alexandr Wang’s thing) got billion dollar valuations with no path to profitability and no revenue.
It seems that ROI has become more important in the last 5 years, but then again you have these Space or Rare Earth shitcos trading at -200x PE while all of their industrial promise is directly undermined by rising costs from AI.
The likely forecast for this year is either rate hikes combined with further labor market deterioration and consumption somehow going negative, or inflation eating up all of the (still non existent) profits from AI mega caps themselves.
It’s hard to see how this ends well without a lowered cost of capital or more interest in taking on capex risk, which seems frankly unlikely. The worst case scenario seems to be a lot of bad debt with nobody except for perhaps Berkshire or China who would be interested or capable when it comes to salvaging it. Armchair economist here, grain of salts a plenty.
A lot of times the act of specifying test criteria prevents developers from accidentally vibe coding themselves into a bad implementation. You can then read the tests and verify that it does what you want it to. You can read the code!
I’m not saying that it’s all hunky dory, but you use AI for straight up test driven development to catch edge cases and correct sloppy implementations before they even get coded by your giant chaos machine.
I think you can understand that line of reasoning, but you can question its feasibility. You might not have any “star coders”, nor need them day-to-day, but I think the cost of not having one true expert, or having a completely vibe coded system that crashes in production will be extremely high.
Is it that incomprehensible that you might want to limit healthcare offerings to lawful residents only, or that the government might track metadata about how services are doing so, regardless of how they choose to take action on it?
This is a great reason not to identify too much with your work. I have enjoyed AI because it has reminded me that my real calling is art, and that I should be doing that at 8 pm, not coding
I don’t think anyone’s true calling is coding. That’s like saying you really like the act of writing, so much that you’d become a stenographer or a typist or something where you do zero higher level thinking and just absent mindedly press buttons.
Most people who are good at tech hate coding so much that they come up with elaborate abstractions so that they can avoid doing more of it.
I recommend you read the post because that's a really bad misunderstanding of the mindset, and like the comment at the top of this chain says, the post explains it well.
I read the post. I don’t agree with the “people are born to do one thing” mindset. There’s a lot of possibilities out there for everyone. I do identify with this OP fellow somewhat, except that I usually don’t code for fun on nights and weekends (also sunday code sesh can be fun)
Not sure if your 'enjoyed AI' is meant literally. I have escaped my existential crisis and found solace in art as well, simply because it's a very human method of self-expression and taking shortcuts to pain, effort and creativity by prompting LLMs is still frowned upon, at least by those that take art seriously.
The only way I can still enjoy programming now is if it's applied to artistic endeavours. I'm done with the soulless, cost-efficient software "engineering" (which by itself is a laughable proposition and a far cry from the high standards of other fields of engineering)
I do literally enjoy working with AI sometimes, other times it is hell. But sometimes coding by hand is hell, too, usually when working on other people’s extremely hacky and procedural code.
I used to believe in alert fatigue, because you’re frequently told to repeat the line: if you have too many alerts, eventually everyone will stop paying attention to them.
I have tons of alerts at work. They go to specialized slack channels that I can look at if I need. We have on call escalation paths for critical ones and housekeeping duties for the ones that require engineers to perform a maintenance task. We have the hell channels that are 99.99% flapping, if you ever need that.
I find that observability in general has an extremely linear marginal reward curve, it basically always justifies the effort you put into setting it up.
Maybe because Anthropic are trying to get to an IPO and everything is securities fraud?
If their CEO was just flapping his mouth without any other comparable baseline, it'd probably be different. But as the GP points out, open-weight model providers are charging comparable rates and very likely have positive profit margins. That would imply that with API pricing tokens are sold at above cost.
That cost may well be "inference only", so excludes everything apart from hardware and power. Whether that's enough to cover the enormous training costs and other overheads is a different question.
He just told you. Because overwhelming public evidence supports the claim. Especially the pricing of open weight model inference. Why do you allow a prejudice to overshadow evidence?
reply