the model does not make the architecture decisions, you make the architecture decisions. you define what success is, including performance characteristics. fuzzing and property based testing ensure correctness. what…
But that's just more data. Create the error conditions in your test harness and exercise them. The machine will tell you what happened. Then correct the machine.
You build your outcome conditions and specifications in code as well. And you iterate on them too. I'm not talking about waterfall development. It's something else. You can spend a day just prototyping, spiking,…
Code is not literature. It's not poetry. It does not express the human spirit. Code is a machine made of symbols. Engineers do care about the beauty of their machine designs, but in the end what matters is whether the…
writing is a form of thinking, but there are others
This shit is absurd. Just decide whether Fable will be part of the subscription model or not. Are you losing too much money on it to be profitable? Say so. Did you see signups tank and lose a huge amount of users to…
We're about the same age, I was even in a band at a small liberal arts college in the great lakes area in 2003. AI can't bring it back, and the stuff the music AI has created here sounds terrible to me.
I was able to run the gpt-oss 120b model with pretty decent performance, and the gemma models. I haven't experimented yet with qwen3 on here much. I always assumed CPU inference would suck, and it was built as a…
Tried this out on my ThreadRipper: AMD Ryzen Threadripper PRO 5975WX — 32 cores / 64 threads, Zen3 (znver3), AVX2+FMA (no AVX-512/VNNI), 128GB RAM, Kingston SKC3000D 4TB NVMe (PCIe4). Disk gets around 7GB/s. It took a…
the math involved is not very hard to understand. it’s linear algebra. the transformer model is brilliant but simple, nobody even really realized the impact it would have until they started training it on massive…
on Plus I see Terra and Luna, but not Sol
"objectively the best"?
Sure, macros are functions that take functions as input, and produce new functions as output. But they take the function's symbols as input and produce a new set of symbols. So a macro can extend the syntax of the…
Use whatever you like, but I'd love an elaboration on "The macOS I know and love dying". I haven't loved some of the UX design decisions in the recent macOS releases, but it doesn't feel that different than it did 10…
Not really sure what you mean? You have to use `unsafe` in Rust to access arbitrary mutable pointers. How would you do DMA, or write a device driver, without `* mut T`
twitter was "acquired" by xAI which was then "acquired" by SpaceX as part of the IPO strategy, (and part of a strategy of giving the investors on the hook for the twitter acquisition a return). Who knows how it…
It's difficult to say if a kernel written in rust would not have similar vulnerabilites, because it would be impossible to build a kernel without significant amounts of `unsafe`.
work from tests to implementation. Validate the tests, and work with the agent to ensure there are not more cases that need testing. Then you can let the agent implement the code and you can refine it until it's simple…
I was worried this time last year that by this time this year, companies would have slashed their engineering teams down to a handful and everything would be driven by mostly autonomous agents with human guidance. But…
a button that debounces requests should be disabled until the action is complete instead, so you can only click it once until it is ready to be clicked again. debouncing button clicks is a design failure (it makes more…
AI can code. I've been programming since 1996 but I don't write code anymore, I iterate with an agent. But you only get good output with a human directing it. It's overrated because it requires human direction to…
yes but the americans are also doing it, and i don’t really work on anything worth spying on
lol they can absolutely afford TAs, i don’t know why they might reduce class slots but that’s not why
my M1 mac studio from 2022 is still going strong and i can't see a reason to replace it in the next few years anyway
GLM-5.2 is a huge model. I don't think it would fit on the AI HAT+ 2 even if you quantized it to 2 bits
the model does not make the architecture decisions, you make the architecture decisions. you define what success is, including performance characteristics. fuzzing and property based testing ensure correctness. what…
But that's just more data. Create the error conditions in your test harness and exercise them. The machine will tell you what happened. Then correct the machine.
You build your outcome conditions and specifications in code as well. And you iterate on them too. I'm not talking about waterfall development. It's something else. You can spend a day just prototyping, spiking,…
Code is not literature. It's not poetry. It does not express the human spirit. Code is a machine made of symbols. Engineers do care about the beauty of their machine designs, but in the end what matters is whether the…
writing is a form of thinking, but there are others
This shit is absurd. Just decide whether Fable will be part of the subscription model or not. Are you losing too much money on it to be profitable? Say so. Did you see signups tank and lose a huge amount of users to…
We're about the same age, I was even in a band at a small liberal arts college in the great lakes area in 2003. AI can't bring it back, and the stuff the music AI has created here sounds terrible to me.
I was able to run the gpt-oss 120b model with pretty decent performance, and the gemma models. I haven't experimented yet with qwen3 on here much. I always assumed CPU inference would suck, and it was built as a…
Tried this out on my ThreadRipper: AMD Ryzen Threadripper PRO 5975WX — 32 cores / 64 threads, Zen3 (znver3), AVX2+FMA (no AVX-512/VNNI), 128GB RAM, Kingston SKC3000D 4TB NVMe (PCIe4). Disk gets around 7GB/s. It took a…
the math involved is not very hard to understand. it’s linear algebra. the transformer model is brilliant but simple, nobody even really realized the impact it would have until they started training it on massive…
on Plus I see Terra and Luna, but not Sol
"objectively the best"?
Sure, macros are functions that take functions as input, and produce new functions as output. But they take the function's symbols as input and produce a new set of symbols. So a macro can extend the syntax of the…
Use whatever you like, but I'd love an elaboration on "The macOS I know and love dying". I haven't loved some of the UX design decisions in the recent macOS releases, but it doesn't feel that different than it did 10…
Not really sure what you mean? You have to use `unsafe` in Rust to access arbitrary mutable pointers. How would you do DMA, or write a device driver, without `* mut T`
twitter was "acquired" by xAI which was then "acquired" by SpaceX as part of the IPO strategy, (and part of a strategy of giving the investors on the hook for the twitter acquisition a return). Who knows how it…
It's difficult to say if a kernel written in rust would not have similar vulnerabilites, because it would be impossible to build a kernel without significant amounts of `unsafe`.
work from tests to implementation. Validate the tests, and work with the agent to ensure there are not more cases that need testing. Then you can let the agent implement the code and you can refine it until it's simple…
I was worried this time last year that by this time this year, companies would have slashed their engineering teams down to a handful and everything would be driven by mostly autonomous agents with human guidance. But…
a button that debounces requests should be disabled until the action is complete instead, so you can only click it once until it is ready to be clicked again. debouncing button clicks is a design failure (it makes more…
AI can code. I've been programming since 1996 but I don't write code anymore, I iterate with an agent. But you only get good output with a human directing it. It's overrated because it requires human direction to…
yes but the americans are also doing it, and i don’t really work on anything worth spying on
lol they can absolutely afford TAs, i don’t know why they might reduce class slots but that’s not why
my M1 mac studio from 2022 is still going strong and i can't see a reason to replace it in the next few years anyway
GLM-5.2 is a huge model. I don't think it would fit on the AI HAT+ 2 even if you quantized it to 2 bits