When accusing someone of "good looking lies", it would help to provide an example or two with an explanation of why you think they're lies (rather than mistakes, oversights or differences of opinion). Complaints that…
Can you point out exactly where it says that? As I read it, the claim is that AI boosts the productivity of writing code to the point that it's usually not productive for humans to write code directly. I think that…
Probably just you. I use them somewhat frequently to make it clear where a set breaks down into alternatives or parallel factors. If there's a preface and trailer around a list of complex items, I think writing the list…
Yes, people are entitled to their emotions, but the ways they behave in public and express their emotions reflects on them in a major way. The Bun blog post focused on the technical reasons to change, and was…
[dead]
U2F was always an option, because I used it since they added the MFA requirement (and like others here never gave Github my phone number). I think TOTP was also available from the start. The warning to not use SMS for…
Those are the ratios for memory bandwidth, but the GPUs have a much higher ratio for compute, and that affects prefill rate / TTFT, right?
Yes, all of those and more. Our measurement precision is much better than the year-to-year first and second derivatives of day length. https://datacenter.iers.org/singlePlot.php?plotname=Bulletin... has the most…
IMO, "make your servers fungible" is a better way to express the intent: slightly shorter, no metaphors, although "fungible" is a less common word. Maybe that's just me.
Can you elaborate on the distinction between "eliminate the hazard" as the first choice and "engineering out the hazard" as a fallback approach? In my safety background (recently aerospace, ARP4754/4761), removing and…
My experience is that AI agents write 20-33% more code than I would for a given feature set, mostly because they are worse at remembering what utility functions already exist and less likely to merge similar functions…
I think you're overlooking the lesson of Goodhart's law: you can use a metric, but if you make it a target, it stops being a good metric. Neither "tons of aircraft" nor "lines of code" should be the measuring stick --…
It is hard to have much sympathy for someone who complains about seeing a Git commit they never made but presumably clicked "publish" for a blog post that says "a North Korea-aligned group who targets software…
In this case, "Zero-JS" seems to mean that you write short bits of JavaScript that look like a domain-specific language, and you include a relatively small JavaScript file that translates certain server-sent events into…
A single benefit usually has an appropriate incentive structure, but a lot of people get multiple benefits -- even from different levels of government (local, state, federal) -- and adding up phase-outs in different…
Perhaps to support demand for the products with recent price hikes, and/or the upcoming Mac Studio with M5 Ultra, rather than have customers sit on the sidelines thinking they'll wait this generation out. I am still…
The mechanism is that generating tokens (the "decode" phase) in an LLM is limited by memory bandwidth for the weights, so computing multiple streams amortizes the bandwidth over streams as long as you can keep the…
> The DGX Spark has basically the same memory bandwidth as a M5 Pro, and far more than a M5. I see ~274 GB/sec for the DGX Spark[1], versus 307 GB/sec for M5 Pro and 460 or 614 GB/sec for M5 Max[2]. One might call 90%…
For coding, Qwen3.6-27B with MTP should fit in 32GB with almost full context length for Unsloth's 5-bit quantization. That's my preferred choice for a local coding agent on similar hardware: the quality delta compared…
HuggingFace says this model has 753B parameters, which will need a lot more RAM than a maxed-out MacBook Pro. With 40B active parameters, running from SSD would need patience.
The answer to the question posed in the site's domain name is "no", unfortunately. It looks like it just grabbed the intro to each project's self-description, but blurbs like "Zero-cost ultra-high-performance…
Ignoring multiple evaluation, one can also #define stdc_has_single_bit(X) !((X) & ((X)-1)). If X isn't a power of two, the -1 will leave the MSB in place.
Yes, but presumably the authors are suggesting broader application than just caching a system prompt. The paper's approach should work well if (a) you can calculate KV(A || B) as a function of KV(A) and KV(B)…
Perhaps I overlooked something, but which part of this involved "fooling Go"? I would usually not call it "fooling" something to trigger a not-strictly-required rejection of a dubious trait, especially when best…
And the Russian system is named (the Russian words for) "Global Navigation Satellite System", but usually only called GLONASS because adding L, O and A is less confusing than having one name for super- and sub-sets in a…
When accusing someone of "good looking lies", it would help to provide an example or two with an explanation of why you think they're lies (rather than mistakes, oversights or differences of opinion). Complaints that…
Can you point out exactly where it says that? As I read it, the claim is that AI boosts the productivity of writing code to the point that it's usually not productive for humans to write code directly. I think that…
Probably just you. I use them somewhat frequently to make it clear where a set breaks down into alternatives or parallel factors. If there's a preface and trailer around a list of complex items, I think writing the list…
Yes, people are entitled to their emotions, but the ways they behave in public and express their emotions reflects on them in a major way. The Bun blog post focused on the technical reasons to change, and was…
[dead]
U2F was always an option, because I used it since they added the MFA requirement (and like others here never gave Github my phone number). I think TOTP was also available from the start. The warning to not use SMS for…
Those are the ratios for memory bandwidth, but the GPUs have a much higher ratio for compute, and that affects prefill rate / TTFT, right?
Yes, all of those and more. Our measurement precision is much better than the year-to-year first and second derivatives of day length. https://datacenter.iers.org/singlePlot.php?plotname=Bulletin... has the most…
IMO, "make your servers fungible" is a better way to express the intent: slightly shorter, no metaphors, although "fungible" is a less common word. Maybe that's just me.
Can you elaborate on the distinction between "eliminate the hazard" as the first choice and "engineering out the hazard" as a fallback approach? In my safety background (recently aerospace, ARP4754/4761), removing and…
My experience is that AI agents write 20-33% more code than I would for a given feature set, mostly because they are worse at remembering what utility functions already exist and less likely to merge similar functions…
I think you're overlooking the lesson of Goodhart's law: you can use a metric, but if you make it a target, it stops being a good metric. Neither "tons of aircraft" nor "lines of code" should be the measuring stick --…
It is hard to have much sympathy for someone who complains about seeing a Git commit they never made but presumably clicked "publish" for a blog post that says "a North Korea-aligned group who targets software…
In this case, "Zero-JS" seems to mean that you write short bits of JavaScript that look like a domain-specific language, and you include a relatively small JavaScript file that translates certain server-sent events into…
A single benefit usually has an appropriate incentive structure, but a lot of people get multiple benefits -- even from different levels of government (local, state, federal) -- and adding up phase-outs in different…
Perhaps to support demand for the products with recent price hikes, and/or the upcoming Mac Studio with M5 Ultra, rather than have customers sit on the sidelines thinking they'll wait this generation out. I am still…
The mechanism is that generating tokens (the "decode" phase) in an LLM is limited by memory bandwidth for the weights, so computing multiple streams amortizes the bandwidth over streams as long as you can keep the…
> The DGX Spark has basically the same memory bandwidth as a M5 Pro, and far more than a M5. I see ~274 GB/sec for the DGX Spark[1], versus 307 GB/sec for M5 Pro and 460 or 614 GB/sec for M5 Max[2]. One might call 90%…
For coding, Qwen3.6-27B with MTP should fit in 32GB with almost full context length for Unsloth's 5-bit quantization. That's my preferred choice for a local coding agent on similar hardware: the quality delta compared…
HuggingFace says this model has 753B parameters, which will need a lot more RAM than a maxed-out MacBook Pro. With 40B active parameters, running from SSD would need patience.
The answer to the question posed in the site's domain name is "no", unfortunately. It looks like it just grabbed the intro to each project's self-description, but blurbs like "Zero-cost ultra-high-performance…
Ignoring multiple evaluation, one can also #define stdc_has_single_bit(X) !((X) & ((X)-1)). If X isn't a power of two, the -1 will leave the MSB in place.
Yes, but presumably the authors are suggesting broader application than just caching a system prompt. The paper's approach should work well if (a) you can calculate KV(A || B) as a function of KV(A) and KV(B)…
Perhaps I overlooked something, but which part of this involved "fooling Go"? I would usually not call it "fooling" something to trigger a not-strictly-required rejection of a dubious trait, especially when best…
And the Russian system is named (the Russian words for) "Global Navigation Satellite System", but usually only called GLONASS because adding L, O and A is less confusing than having one name for super- and sub-sets in a…