I tried the qwen3.6-27b Q6_k GUFF in llama.cpp and LM Studio on my M2 MacBook Pro 32GB machine last week, and I barely get a token a second with either. The fact that it was this slow makes me suspect it's a matter of…
It's highly improbable that the US government has a secret team inside Anthropic and OpenAI manipulating their training regimen. Two thoughts. One: it would be relatively technically trivial for $GOVERNMENT_AGENCY to…
Yeah, at this point I think the worst-case scenario for OpenAI/Anthropic/etc is to slow down frontier model development and focus on tooling and services, as opposed to imploding completely and bursting the economic…
Prevailing wisdom is that serving LLMs at a profit is achievable... it's when you factor in the cost of training them that prices get astronomical real fast. Open-source model inference providers (who do not have to…
All I really want from a database IDE is awesome autocomplete for identifiers and keywords. (I consider SQL Server Management Studio's autocomplete to be great - if I could get that for Postgres, I'd be thrilled) You…
I was that way when I was younger. As I hit my thirties I found myself becoming a "morning person." Anecdotally, I find this is super common. I actually enjoy early-morning coding (before the rest of the world wakes up)…
Sure, I perfectly understand how bars work. Like you say, it's totally possible nobody at the bar knew this woman was being harassed. Especially if this guy has plenty of experience being a creep and has gotten good at…
I've been in this conference organizer's shoes before. On one hand, running a conference/convention is difficult enough without being asked to referee personal conflicts. It almost inevitably devolves into a…
I tried the qwen3.6-27b Q6_k GUFF in llama.cpp and LM Studio on my M2 MacBook Pro 32GB machine last week, and I barely get a token a second with either. The fact that it was this slow makes me suspect it's a matter of…
It's highly improbable that the US government has a secret team inside Anthropic and OpenAI manipulating their training regimen. Two thoughts. One: it would be relatively technically trivial for $GOVERNMENT_AGENCY to…
Yeah, at this point I think the worst-case scenario for OpenAI/Anthropic/etc is to slow down frontier model development and focus on tooling and services, as opposed to imploding completely and bursting the economic…
Prevailing wisdom is that serving LLMs at a profit is achievable... it's when you factor in the cost of training them that prices get astronomical real fast. Open-source model inference providers (who do not have to…
All I really want from a database IDE is awesome autocomplete for identifiers and keywords. (I consider SQL Server Management Studio's autocomplete to be great - if I could get that for Postgres, I'd be thrilled) You…
I was that way when I was younger. As I hit my thirties I found myself becoming a "morning person." Anecdotally, I find this is super common. I actually enjoy early-morning coding (before the rest of the world wakes up)…
Sure, I perfectly understand how bars work. Like you say, it's totally possible nobody at the bar knew this woman was being harassed. Especially if this guy has plenty of experience being a creep and has gotten good at…
I've been in this conference organizer's shoes before. On one hand, running a conference/convention is difficult enough without being asked to referee personal conflicts. It almost inevitably devolves into a…