That’s well and good, but how are we supposed to evaluate the accuracy of random HN comments without anything resembling somewhat objective metrics? People say all manner of things, and usually it’s contradictory. What heuristic do you propose?
set up a rendering profile and preconditions that generates a minimal snippet of images/video using a predefined GPU profile.
then test for either a pixel perfect reproduction of the correct behaviour or for the properties you're looking for (if it doesnt reproduce deterministically).
this is one way. i also subscribe to the view that if the type system is modified to become stricter in such a way that it can fail reliably in the presence of this type of bug that this is also good enough.
some people might argue that these arent "strictly" TDD by some definition but they set out a path to follow red green refactor and confer identical benefits so my view is who gives a duck?
I don't have enough domain expertise to know which variant of these approaches is best but I'm enough of a TDD expert to know that what you're implying isnt possible is actually something you would would probably derive a lot of value from if you did it.
The typical playbook for a VC funded startup is to race to a monopoly where the company can have higher margins. Prices continuing to go down for the consumer over time would require competition to stay high in the long term, and even then it’s not clear if even current prices are profitable.
The current level of AI has plenty of inherent competition from local models. In the long term, most of the profit will probably be from very smart models that run at something closer to datacenter scale over long inference loops - where local inference can't do much and even third-party inference/small neoclouds will be severely challenged. That is a very natural "moat" and has natural cross-efficiencies with AI model training, which requires a similar scale.
I had that for a few months and cancelled. They have minutely rate limits as well so you get 3-4 hyperspeed responses and then a 45 second pause waiting for the throttling to let your next request through.
And then, depending on what you're working on, the 24M daily allotment is gone in under an hour. I regularly burned it in about 25 minutes of agent use.
I imagine if I had infinite budget to pay regular API rates on a high usage tier, it would be really quite good though.
> They have minutely rate limits as well so you get 3-4 hyperspeed responses and then a 45 second pause waiting for the throttling to let your next request through.
I haven’t really gotten that, though have noticed on some occasions:
A) high server load notifications, most commonly, can delay an answer by about 3-10 seconds
B) hangs, this happens quite rarely, not sure if a network issue or something on their side, but sometimes the submitted message just freezes (e.g. nothing happening in OpenCode), doesn’t seem deliberate because resubmitting immediately works, more often than not
> And then, depending on what you're working on, the 24M daily allotment is gone in under an hour. I regularly burned it in about 25 minutes of agent use.
That’s a lot of tokens, almost a million a minute! Since the context is about 128k, you’d be doing about 8 full context requests every minute for 25 minutes straight.
I can see something like that, but at that point it feels like the only thing that’d actually be helpful would be caching support on their end.
You must be on some pretty high tier subscriptions with the other providers to get the same performance!
Interesting. I'm also nearsighted, so I've always assumed that I don't need glasses when wearing VR headsets. It's easier to just take them off before putting on the headset (MQ3) and I've not noticed a difference in clarity — but I do experience eye strain and visual exhaustion if I wear the headset for too long, so it might be worth comparing longer sessions with and without glasses.
Nothing's stopping users who want an AI summary from feeding the content into their favourite GPT. But it's not contributing anything meaningful to a HN discussion.
