Hacker News: paoliniluis

New comment by paoliniluis in "Xiaomi MiMo-v2.5-Pro Open-Sourced: 1T Parameter Model"

paoliniluis — Tue, 28 Apr 2026 15:00:59 +0000

They claim they're surpassing the latest DeepSeek model in many tests. I'm wondering when we can see a GGUF release of this model as being a MoE this should run fine on local machines.

BTW: here's the blog post https://mimo.xiaomi.com/mimo-v2-5-pro. They state that "DeepSeek V4 Pro numbers are with its max effort setting." so I'm wondering what they used for this one.

New comment by paoliniluis in "Google broke its promise to me – now ICE has my data"

paoliniluis — Wed, 15 Apr 2026 18:26:27 +0000

Agree. Google can't go against the all-mighty state. Just look at what Anthropic did and the effect of that action. There are billions of dollars at stake on government contracts that they can't afford to lose. Reminds me of Mullvad's ad https://www.youtube.com/watch?v=fPzvUW8qaWY

New comment by paoliniluis in "Bitcoin miners are losing on every coin produced as difficulty drops"

paoliniluis — Sat, 11 Apr 2026 14:41:06 +0000

It's 2026 and there's still people that believe that proof-of-work makes sense as a consensus mechanism

New comment by paoliniluis in "Project Glasswing: Securing critical software for the AI era"

paoliniluis — Wed, 08 Apr 2026 00:50:53 +0000

Does everyone agrees that this makes Dario Amodei more powerful than any politician across the world? Anthropic is now the owner of the most powerful cyberweapon ever made

New comment by paoliniluis in "EmDash – A spiritual successor to WordPress that solves plugin security"

paoliniluis — Wed, 01 Apr 2026 17:39:58 +0000

Who wants to vibe code an open source Cloudflare?

New comment by paoliniluis in "LinkedIn uses 2.4 GB RAM across two tabs"

paoliniluis — Sun, 29 Mar 2026 12:53:11 +0000

LinkedIn feed now brings dumb posts from AI bots that contacts follow. All social networks tend to follow the same principles now: bring to everyone’s feed what’s most engaging, which is normally clickbaits or posts that use exaggerated words

New comment by paoliniluis in "How to run Qwen 3.5 locally"

paoliniluis — Sun, 08 Mar 2026 17:32:19 +0000

run ollama show : and you'll get the info. E.g. ollama show qwen3.5:0.8b Model architecture qwen35 parameters 873.44M context length 262144 embedding length 1024 quantization Q8_0 requires 0.17.1

  Capabilities
    completion    
    vision        
    tools         
    thinking      

  Parameters
    presence_penalty    1.5     
    temperature         1       
    top_k               20      
    top_p               0.95    

  License
    Apache License               
    Version 2.0, January 2004

New comment by paoliniluis in "How to run Qwen 3.5 locally"

paoliniluis — Sun, 08 Mar 2026 17:06:57 +0000

just finding the perfect spot between accuracy of the answers/available VRAM/tokens per second

New comment by paoliniluis in "Something is afoot in the land of Qwen"

paoliniluis — Wed, 04 Mar 2026 16:32:42 +0000

what's your take between Qwen3.5-35B-A3B and Qwen3-Coder-Next?