Disclaimer, I only use it to grow the "knowledge hub". It's a single git project at my $USER home, that is referenced in global memory. It contains as much information about work things, as possible, to be productive. I…
That's where the annotation in plannotator helps. I'm asking to scan projects on gitlab, go through some docs to find more grounding material, write a subarticle (in the same style), scan logs on the test env, issue…
Oh, I know exactly what you mean. I use plannotator with claude a lot and have much better time, since I asked for a specific styleguide. I used "CD era MSDN reference and Raymond Chen blogging style" as a starting…
Similarly, I never try to imagine a bright sunshine. It can wake me up
There never are. Those are going to be viewed as two discreet successful interventions. One for lay-offs, because it was the best move at the time with the knowledge they had. Second for quick correction, ability to…
I remember seeing this popping up in discussions the first time, but never noticed any resolution (other than to train both sides). Has SOTA advanced?
> A shift is happening among major AI labs, who are becoming increasingly skeptical of endless parameter count and training data scaling I'm pretty sure it's mostly due to the training data quality. No idea, why this…
Noticed few cliffs. Sometimes it was a spurious stop (had to write "go on" or "continue" to restart), othertimes it was randomly saying: "Oh the user wants [the thing we already resolved]" and goes back in history.…
If I started today, with building a server, I'd jump right into verified set-ups and writeups, like this one: https://github.com/noonghunna/club-3090 You can find info about running a patched version of vllm for 1x24gb,…
> The model is running so hot, that it shoots past the goal and starts looping later: > My latest experiment was setting up vLLM (the gold standard for production and concurrent serving) and even with an NVLink (175GBP)…
I'm still sour they had only one toast in, in a two slot toaster
Also, supposedly biggest MMA event Rogan doesn't want to be on. Something is up
I kept getting recipes with "that one ingredient", which was either a major PITA to source or produced too much waste, even from a real world dietician consultation. Example, use 1/4th of a pumpkin for something. Those…
Chrome driven by the OS accessibility API
I keep finding more and more usecases for Q3.6 27b (same league) and the best performance is, when answers to my question is already in the context. The moment I'm trying something open-ended or ambitious,…
Yeah, it won't. SWE here with a sidegoal to tackle the deployment side through various means (homelabbing, grabbing sre/cloud/observability tasks at work). The biggest observable improvement in my post and pre ai…
It feels now like an alternative timeline, one which performance optimisations were first and foremost still. Sometimes I fantasize, thinking how would our current development ecosystem look like, if we never abandoned…
Batching lowers that, since the model is read once from memory. Activation accumulation doesn't scale as nicely
On my homelab. It really feels like a dream come true for my usecase. No more puppet agents. No more declarative syntax, that you have to work around to do basic imperative ways. Or use a module, that stopped being…
Yes, my goes either-or quite abruptly and, while that's not really annoying, I notice it doing way too often, than I'd like to. It shouldn't be done in a binary fashion as well.
Touchscreens can also leave fingerprints and those will catch light at any angle and reduce effective contrast
Never understood any appeal of a screen inside a car: 1. Reflections make you tilt, just to make some pesky highlights go away. Even if they are angled properly, there's always something (like a sun reflected by a…
3090s
I'm adding two extra gpus to my local rig. Turns out qwen 3.5 122b is already enough to handle (finish with moderate guidance) non-planning parts of my tasks.
That's actually a good case for a LLM going through it and deciding: "nah, overblown" and "Oh, yeah, this one can close the account"
Disclaimer, I only use it to grow the "knowledge hub". It's a single git project at my $USER home, that is referenced in global memory. It contains as much information about work things, as possible, to be productive. I…
That's where the annotation in plannotator helps. I'm asking to scan projects on gitlab, go through some docs to find more grounding material, write a subarticle (in the same style), scan logs on the test env, issue…
Oh, I know exactly what you mean. I use plannotator with claude a lot and have much better time, since I asked for a specific styleguide. I used "CD era MSDN reference and Raymond Chen blogging style" as a starting…
Similarly, I never try to imagine a bright sunshine. It can wake me up
There never are. Those are going to be viewed as two discreet successful interventions. One for lay-offs, because it was the best move at the time with the knowledge they had. Second for quick correction, ability to…
I remember seeing this popping up in discussions the first time, but never noticed any resolution (other than to train both sides). Has SOTA advanced?
> A shift is happening among major AI labs, who are becoming increasingly skeptical of endless parameter count and training data scaling I'm pretty sure it's mostly due to the training data quality. No idea, why this…
Noticed few cliffs. Sometimes it was a spurious stop (had to write "go on" or "continue" to restart), othertimes it was randomly saying: "Oh the user wants [the thing we already resolved]" and goes back in history.…
If I started today, with building a server, I'd jump right into verified set-ups and writeups, like this one: https://github.com/noonghunna/club-3090 You can find info about running a patched version of vllm for 1x24gb,…
> The model is running so hot, that it shoots past the goal and starts looping later: > My latest experiment was setting up vLLM (the gold standard for production and concurrent serving) and even with an NVLink (175GBP)…
I'm still sour they had only one toast in, in a two slot toaster
Also, supposedly biggest MMA event Rogan doesn't want to be on. Something is up
I kept getting recipes with "that one ingredient", which was either a major PITA to source or produced too much waste, even from a real world dietician consultation. Example, use 1/4th of a pumpkin for something. Those…
Chrome driven by the OS accessibility API
I keep finding more and more usecases for Q3.6 27b (same league) and the best performance is, when answers to my question is already in the context. The moment I'm trying something open-ended or ambitious,…
Yeah, it won't. SWE here with a sidegoal to tackle the deployment side through various means (homelabbing, grabbing sre/cloud/observability tasks at work). The biggest observable improvement in my post and pre ai…
It feels now like an alternative timeline, one which performance optimisations were first and foremost still. Sometimes I fantasize, thinking how would our current development ecosystem look like, if we never abandoned…
Batching lowers that, since the model is read once from memory. Activation accumulation doesn't scale as nicely
On my homelab. It really feels like a dream come true for my usecase. No more puppet agents. No more declarative syntax, that you have to work around to do basic imperative ways. Or use a module, that stopped being…
Yes, my goes either-or quite abruptly and, while that's not really annoying, I notice it doing way too often, than I'd like to. It shouldn't be done in a binary fashion as well.
Touchscreens can also leave fingerprints and those will catch light at any angle and reduce effective contrast
Never understood any appeal of a screen inside a car: 1. Reflections make you tilt, just to make some pesky highlights go away. Even if they are angled properly, there's always something (like a sun reflected by a…
3090s
I'm adding two extra gpus to my local rig. Turns out qwen 3.5 122b is already enough to handle (finish with moderate guidance) non-planning parts of my tasks.
That's actually a good case for a LLM going through it and deciding: "nah, overblown" and "Oh, yeah, this one can close the account"