Still not going for it. Once I learned I can train Qwen3.8 27B with my style of writing/grammar. Also more succinct. I cannot force myself to Claude or OpenAI outputs anymore. Its too much. Honestly don't think I will…
I've been using ComfyUI to do fine background and watermark removal. Might take a look into that as an alternative. Run Flux.2 Klein or Comfyui's own workflow.
I've had great success with allowing the model to review optimal settings and my system specs. It comes up with the right configuration. Running Pi harness. I just had Ornith 1.5 take a moment to configure itself, now…
Meme: "I'm doing my part" Starship Troopers.
I've been using Gemini as an advance search engine. Their main search with AI isn't that useful but Gemini is. They're the only AI online I will use and just for searching/compiling. For work/development it is Qwen3.8.…
Sweet. Going to make Pi help make Pi music. Just have to vibe code some method but this will be enjoyable.
I'll never allow anything related by META to touch my system/workflow. They're a cancer and I will stick to that. I see 0 good from this.
This can be said for a lot of different matters. Reading this gave me some Déjà vu vibes. My personal take, I don't see this as a good thing. Yes I dislike META with a passion and will refuse to use this model or allow…
Slowly killing my lawn. Red bud trees will soon forest my property.
Thank you, that is very useful for my use case. Pi has transformed so much of my daily task, this will boost it a bit more. Much appreciated.
Worth if you plan to use it for production use. If you use it for personal or as mockup, then what they don't know won't hurt them? ;)
That would be the prompt. With the right assistance from Qwen3.5/Ornith I was able to achieve some amazing results. Unfortunately due to their licensing I'm not allowed to use it in the USA, so I had to halt testing.
I would recommend looking into Ornith1.0 - it's using Qwen3.6 35B-A3B and excels in coding, at least for my coding needs, Python, web-dev, SQL scripting and some C#. Using Pi harness.
This. I'm very much happy to see minimax-h3 be released. I have so many projects that I have on the back burner that I could complete within minutes instead of hours and hours. "Typography, UI, and Graphics".
Going to be a wild future that is for sure. I can see many ways this will go, some not so good.
I feel you. I dig this and enjoyed those types of aesthetics. Back in the day this was my bread and butter, designing UI design for games and apps. I just realized AI (Specifically Pi+Ornith) can help with my ideas...…
I really like that design. May I ask the name of the website builder/diagram? Is it Relume?
Would it be possible to use your mouse to slide, pan left and right instead of using the direction keys? Assuming it is touch enabled? Just wondering.
I sense the same. Running Ornith 35b with Pi and hitting 50+toks, and now that I learned Pi can do search and fetch, I have not needed to visit any of the large models as a search function. Soon we will be seeing new…
You can using chatterbox and a couple voice to voice models. Sorry I don’t recall the whole process but you can YouTube Star Trek computer voice AI.
Even with Fabel and all that I constantly keep having to babysit it and correct it like it’s an adolescent and it gets really old and the amount of code. It produces not all of its great at all. I’m burnt out looking…
And the kicker is that this could be an ai-agent doing the astroturfing. Now that even the common man can run local ai-agents that can post.
I'm still connecting once in a while to a local (dialup)BBS that has been running since 1994, no growth but we're still keeping in touch. Same for a forum I frequent from time to time, since 2001. I've recently…
Thanks for sharing that. I have the same card but 96gb ram. I use PI.dev to connect to LM-Studio. I may have to switch away from LM-studio if I can improve token speed. I think I range from 32-40t/s.…
I'm running it on my 4070 12gb with 96gb mem, I'm very happy with the results even if I have to wait a couple minutes for results. To me this is far better than I expected and will continue to use it and improve with…
Still not going for it. Once I learned I can train Qwen3.8 27B with my style of writing/grammar. Also more succinct. I cannot force myself to Claude or OpenAI outputs anymore. Its too much. Honestly don't think I will…
I've been using ComfyUI to do fine background and watermark removal. Might take a look into that as an alternative. Run Flux.2 Klein or Comfyui's own workflow.
I've had great success with allowing the model to review optimal settings and my system specs. It comes up with the right configuration. Running Pi harness. I just had Ornith 1.5 take a moment to configure itself, now…
Meme: "I'm doing my part" Starship Troopers.
I've been using Gemini as an advance search engine. Their main search with AI isn't that useful but Gemini is. They're the only AI online I will use and just for searching/compiling. For work/development it is Qwen3.8.…
Sweet. Going to make Pi help make Pi music. Just have to vibe code some method but this will be enjoyable.
I'll never allow anything related by META to touch my system/workflow. They're a cancer and I will stick to that. I see 0 good from this.
This can be said for a lot of different matters. Reading this gave me some Déjà vu vibes. My personal take, I don't see this as a good thing. Yes I dislike META with a passion and will refuse to use this model or allow…
Slowly killing my lawn. Red bud trees will soon forest my property.
Thank you, that is very useful for my use case. Pi has transformed so much of my daily task, this will boost it a bit more. Much appreciated.
Worth if you plan to use it for production use. If you use it for personal or as mockup, then what they don't know won't hurt them? ;)
That would be the prompt. With the right assistance from Qwen3.5/Ornith I was able to achieve some amazing results. Unfortunately due to their licensing I'm not allowed to use it in the USA, so I had to halt testing.
I would recommend looking into Ornith1.0 - it's using Qwen3.6 35B-A3B and excels in coding, at least for my coding needs, Python, web-dev, SQL scripting and some C#. Using Pi harness.
This. I'm very much happy to see minimax-h3 be released. I have so many projects that I have on the back burner that I could complete within minutes instead of hours and hours. "Typography, UI, and Graphics".
Going to be a wild future that is for sure. I can see many ways this will go, some not so good.
I feel you. I dig this and enjoyed those types of aesthetics. Back in the day this was my bread and butter, designing UI design for games and apps. I just realized AI (Specifically Pi+Ornith) can help with my ideas...…
I really like that design. May I ask the name of the website builder/diagram? Is it Relume?
Would it be possible to use your mouse to slide, pan left and right instead of using the direction keys? Assuming it is touch enabled? Just wondering.
I sense the same. Running Ornith 35b with Pi and hitting 50+toks, and now that I learned Pi can do search and fetch, I have not needed to visit any of the large models as a search function. Soon we will be seeing new…
You can using chatterbox and a couple voice to voice models. Sorry I don’t recall the whole process but you can YouTube Star Trek computer voice AI.
Even with Fabel and all that I constantly keep having to babysit it and correct it like it’s an adolescent and it gets really old and the amount of code. It produces not all of its great at all. I’m burnt out looking…
And the kicker is that this could be an ai-agent doing the astroturfing. Now that even the common man can run local ai-agents that can post.
I'm still connecting once in a while to a local (dialup)BBS that has been running since 1994, no growth but we're still keeping in touch. Same for a forum I frequent from time to time, since 2001. I've recently…
Thanks for sharing that. I have the same card but 96gb ram. I use PI.dev to connect to LM-Studio. I may have to switch away from LM-studio if I can improve token speed. I think I range from 32-40t/s.…
I'm running it on my 4070 12gb with 96gb mem, I'm very happy with the results even if I have to wait a couple minutes for results. To me this is far better than I expected and will continue to use it and improve with…