It’s $12k for each Mac Studio, and the networking makes them only effective individually (it’s like less that 15 tokens/s with EXO) while NVLINK is very effective. The Spark is definitely more scalable, but the MLX and…
I run 4 Mac Studio ultras at work (they’re pricy when maxed out), for local-first AI dev services. But there’s a few things that make me want to switch to the Spark. Networking is the biggest one, the Macs have…
EXO is also great for running the 6bit deepseek, plus it’s super handy to serve from all your devices simultaneously. If your dev team all has M3 Max 48gb machines, sharing the compute lets you all run bigger models and…
IQ doesn’t seem to be an ideal metric for macro level civilisation intelligence. A lot of what it optimises for is replaced by technology. If we’re measuring intelligence at that level I’d hope for something like theory…
Fine-tuning mistral for tool use like metasploit is effective, but even default mistral with a basic system prompt is very capable and doesn’t often say it can’t do things. ChatGPT obviously needs a lot of coaxing, “my…
I’m really curious how about how good it used to be? It feels to me like there’s a cultural resistance to be self critical of the whole, and that is slowing down wide-scale progress. I moved to Sweden 2 months ago (from…
How about using an LLM to help you write a MuZero-like model designed for a specific task? (Also MuZero took like 12 hours to train on old hardware, so my MacBook might be good enough here) obviously we’re not here yet,…
I think the subjective time here is especially relevant. The post previous mentioned having a conversation with ChatGPT about the topic. ChatGPT probably had multiple human lifetimes of conversations during that one…
Hey, this is a great idea! I’ve found myself using dating apps for this kind of purpose and I think this could be a better approach, especially from the support side. (I’ve had a few instances where being supportive but…
Ha I just commented above at the pattern of people in this camp using “GTP” fairly consistently. What a curious psychological study, maybe dyslexic people feel more threatened by a large language model so clearly…
Weird behaviour I’ve noticed is a lot of folks on the unimpressed/doomism side of AI consistently say GTP instead of GPT, I wonder why this pattern exists?
Wow I had to go on a nostalgia tour and I found a Rookie classic: https://www.youtube.com/watch?v=FwpujtVM6R8 Bugs really made this game one of a kind, it's sad it would be so hard to replicate. The way he uses strafing…
I dream of the day when I can ask an LLM to write a modern version of AC in Unreal 7... Exploring Dereth with reality level detail would be incredible.
If anyone remembers the days when guys like "Rookie" or the UD's figured this out and mastered it, what a time to be alive! Good ol' AB wars... :)
The bugs in this game lead to some of the greatest gameplay of all time. I think the best bug was the movement possibilities during spell casting from breaking animations. It created one of the most complex and amazing…
Location: Seattle, WA, USA Remote: Yes Willing to relocate: Yes (lived in 5 countries, always enjoy the adventure) Technologies: AWS, OPA, kubernetes, GCP, GitOps, Kali Linux, Go, Python, DevOps, DevSecOps, Pacu, Cyber…
How was this handled before 2020? As far as I was told, corporate macs were still bios locked (or whatever the bios equivalent is for macs)
I’m not sure it’s directly psychoactive as he stated in the post, it does agonise the TRPV1 receptor; but that doesn’t directly create a sense euphoria. When agonised it triggers the production of endogenous anandamides…
“Worked for me” in the title is important here. For me this is great advice. I have exceptionally low cortisol levels and have accidentally slept for over 24 hours many times in my life. Without an alarm I generally…
I was excited to use this for practicing writing Korean. Unfortunately it looks like whatever regex is looking at what I type does not like Korean characters... :/
It’s $12k for each Mac Studio, and the networking makes them only effective individually (it’s like less that 15 tokens/s with EXO) while NVLINK is very effective. The Spark is definitely more scalable, but the MLX and…
I run 4 Mac Studio ultras at work (they’re pricy when maxed out), for local-first AI dev services. But there’s a few things that make me want to switch to the Spark. Networking is the biggest one, the Macs have…
EXO is also great for running the 6bit deepseek, plus it’s super handy to serve from all your devices simultaneously. If your dev team all has M3 Max 48gb machines, sharing the compute lets you all run bigger models and…
IQ doesn’t seem to be an ideal metric for macro level civilisation intelligence. A lot of what it optimises for is replaced by technology. If we’re measuring intelligence at that level I’d hope for something like theory…
Fine-tuning mistral for tool use like metasploit is effective, but even default mistral with a basic system prompt is very capable and doesn’t often say it can’t do things. ChatGPT obviously needs a lot of coaxing, “my…
I’m really curious how about how good it used to be? It feels to me like there’s a cultural resistance to be self critical of the whole, and that is slowing down wide-scale progress. I moved to Sweden 2 months ago (from…
How about using an LLM to help you write a MuZero-like model designed for a specific task? (Also MuZero took like 12 hours to train on old hardware, so my MacBook might be good enough here) obviously we’re not here yet,…
I think the subjective time here is especially relevant. The post previous mentioned having a conversation with ChatGPT about the topic. ChatGPT probably had multiple human lifetimes of conversations during that one…
Hey, this is a great idea! I’ve found myself using dating apps for this kind of purpose and I think this could be a better approach, especially from the support side. (I’ve had a few instances where being supportive but…
Ha I just commented above at the pattern of people in this camp using “GTP” fairly consistently. What a curious psychological study, maybe dyslexic people feel more threatened by a large language model so clearly…
Weird behaviour I’ve noticed is a lot of folks on the unimpressed/doomism side of AI consistently say GTP instead of GPT, I wonder why this pattern exists?
Wow I had to go on a nostalgia tour and I found a Rookie classic: https://www.youtube.com/watch?v=FwpujtVM6R8 Bugs really made this game one of a kind, it's sad it would be so hard to replicate. The way he uses strafing…
I dream of the day when I can ask an LLM to write a modern version of AC in Unreal 7... Exploring Dereth with reality level detail would be incredible.
If anyone remembers the days when guys like "Rookie" or the UD's figured this out and mastered it, what a time to be alive! Good ol' AB wars... :)
The bugs in this game lead to some of the greatest gameplay of all time. I think the best bug was the movement possibilities during spell casting from breaking animations. It created one of the most complex and amazing…
Location: Seattle, WA, USA Remote: Yes Willing to relocate: Yes (lived in 5 countries, always enjoy the adventure) Technologies: AWS, OPA, kubernetes, GCP, GitOps, Kali Linux, Go, Python, DevOps, DevSecOps, Pacu, Cyber…
How was this handled before 2020? As far as I was told, corporate macs were still bios locked (or whatever the bios equivalent is for macs)
I’m not sure it’s directly psychoactive as he stated in the post, it does agonise the TRPV1 receptor; but that doesn’t directly create a sense euphoria. When agonised it triggers the production of endogenous anandamides…
“Worked for me” in the title is important here. For me this is great advice. I have exceptionally low cortisol levels and have accidentally slept for over 24 hours many times in my life. Without an alarm I generally…
I was excited to use this for practicing writing Korean. Unfortunately it looks like whatever regex is looking at what I type does not like Korean characters... :/