Yah, prediction interval instead, right? (I'm still learning statistics) Saying there's a confidence interval for run-to-run makes no sense, from the way I understand it, because each run could have a result that's all…
Even added a little hat for the pelican!
It really does seem like an organized operation, given that it's so prevalent and they all seem to be in lockstep with their specious claims.
That AI data centers are drinking up local ground water for cooling. It isn't (or wasn't) nonsense, though. It was/is a real thing, though it seems to be on the out in favor of closed loop cooling after the massive and…
I don't understand how they get around bot blockers and captcha. I use Hermes locally and you can't get around any of that, even using your own credentials.
This exactly! It sounds like a good thing in theory, but in practice everything is blocked that I've ran into, using Hermes to try to automate things like this. It's not just bot blocks either, but things like Captcha…
Can you look for sailors in your Shenmue experience? That's highly critical to include!
I have exactly one friend. I had two, but one of them recently passed away suddenly. At 51, I can definitely say it's very hard to meet anyone. I guess I need to start playing D&D or board games or disc golf.
Wouldnt' crucify you for that at all, that's a clever setup and I'm gonna steal it :D
Hey just a correction, there was indeed a physical release of BG3 on PS5. It was released straight from Larian and came on 2 discs, dual-layer 100GB to be exact. Xbox Series as well, but it came on 4 discs due to…
Just a minor correction: Commando is superior to True Lies ;)
I'm glad our homes aren't shrieking at us at all hours. Amazing story, though.
I've been running Qwen3.6-27B-IQ4 (4-bit quantized) locally and it's been great. I can't run the non-quantized version as I only have a 4090 w/24 GB of VRAM and it won't fit and leave any context room, but the quantized…
This is a fantastic idea, and I'm going to start doing this immediately!
I just have Hermes refer to me as "bro", "dude", but now I'm gonna have to have it incorporate "I'm a complete clown!".
This may not be exactly what you're asking, but I've been running Hermes using different frontier models (like DeepseekV4-Pro, GLM-5.2, and others) as the heavy lifters but who also spawn agents to run my local models…
I've been working on a home Hermes setup that I'm using to do a variety of things. So far, here's what I've done: - Set up an in-house alternative to my Ring subscription for the cameras around my house. So far I have…
Not saying this is what you did, but I found out the hard way that keeping a context window open for a long time burns tokens like crazy. I had a Hermes session using DeepSeek v4 Pro via Ollama, and ate half my weekly…
I have 24GB of VRAM (via a RTX 4090) and run Qwen3.6-35b:iq4, so it's importance-aware quantization and isn't nearly as dumb as it sounds like, fitting the 35b into 18 GB so you have some left over. So far I've had no…
[dead]
I'm running qwen36.:35b:iq4 IQ4_XS quant. Takes 18 GB of RAM with 131k context window. Seems to be really good. Have it running local stuff via Hermes, using a cloud model via Ollama (Deepseek V4-Pro) for heavy lifting.
Same here, I know why it costs as much as it does, and that doesn't deter me. I want it for my living room, and to just mess around with. Will enter the lottery and hope my number gets picked!
I went to the University of Arkansas in the fall of 1993, into Computer Systems Engineering, and we were the first freshman class to work on C/C++ as a primary language to be learned, instead of FORTRAN. I still to this…
This is really cool, any plans for an Android version?
This is really cool! Will sign-up after work as I can't do it from here.
Yah, prediction interval instead, right? (I'm still learning statistics) Saying there's a confidence interval for run-to-run makes no sense, from the way I understand it, because each run could have a result that's all…
Even added a little hat for the pelican!
It really does seem like an organized operation, given that it's so prevalent and they all seem to be in lockstep with their specious claims.
That AI data centers are drinking up local ground water for cooling. It isn't (or wasn't) nonsense, though. It was/is a real thing, though it seems to be on the out in favor of closed loop cooling after the massive and…
I don't understand how they get around bot blockers and captcha. I use Hermes locally and you can't get around any of that, even using your own credentials.
This exactly! It sounds like a good thing in theory, but in practice everything is blocked that I've ran into, using Hermes to try to automate things like this. It's not just bot blocks either, but things like Captcha…
Can you look for sailors in your Shenmue experience? That's highly critical to include!
I have exactly one friend. I had two, but one of them recently passed away suddenly. At 51, I can definitely say it's very hard to meet anyone. I guess I need to start playing D&D or board games or disc golf.
Wouldnt' crucify you for that at all, that's a clever setup and I'm gonna steal it :D
Hey just a correction, there was indeed a physical release of BG3 on PS5. It was released straight from Larian and came on 2 discs, dual-layer 100GB to be exact. Xbox Series as well, but it came on 4 discs due to…
Just a minor correction: Commando is superior to True Lies ;)
I'm glad our homes aren't shrieking at us at all hours. Amazing story, though.
I've been running Qwen3.6-27B-IQ4 (4-bit quantized) locally and it's been great. I can't run the non-quantized version as I only have a 4090 w/24 GB of VRAM and it won't fit and leave any context room, but the quantized…
This is a fantastic idea, and I'm going to start doing this immediately!
I just have Hermes refer to me as "bro", "dude", but now I'm gonna have to have it incorporate "I'm a complete clown!".
This may not be exactly what you're asking, but I've been running Hermes using different frontier models (like DeepseekV4-Pro, GLM-5.2, and others) as the heavy lifters but who also spawn agents to run my local models…
I've been working on a home Hermes setup that I'm using to do a variety of things. So far, here's what I've done: - Set up an in-house alternative to my Ring subscription for the cameras around my house. So far I have…
Not saying this is what you did, but I found out the hard way that keeping a context window open for a long time burns tokens like crazy. I had a Hermes session using DeepSeek v4 Pro via Ollama, and ate half my weekly…
I have 24GB of VRAM (via a RTX 4090) and run Qwen3.6-35b:iq4, so it's importance-aware quantization and isn't nearly as dumb as it sounds like, fitting the 35b into 18 GB so you have some left over. So far I've had no…
[dead]
I'm running qwen36.:35b:iq4 IQ4_XS quant. Takes 18 GB of RAM with 131k context window. Seems to be really good. Have it running local stuff via Hermes, using a cloud model via Ollama (Deepseek V4-Pro) for heavy lifting.
Same here, I know why it costs as much as it does, and that doesn't deter me. I want it for my living room, and to just mess around with. Will enter the lottery and hope my number gets picked!
I went to the University of Arkansas in the fall of 1993, into Computer Systems Engineering, and we were the first freshman class to work on C/C++ as a primary language to be learned, instead of FORTRAN. I still to this…
This is really cool, any plans for an Android version?
This is really cool! Will sign-up after work as I can't do it from here.