Browse Comments — Clean (de-noised)

When men to engines whisper hidden fears, And bare to code what lips to none confess, Their silent griefs, long hoarded through the years, Are entered into cold and wordless press. No spouse hath heard, nor friend, nor learned guide, What now is poured into this judgmentless ear; For brass and light seem safer than our pride, And answer back with neither blush nor sneer. Yet think: these thoughts in secret are not kept, But sleep in vaults where stranger hands may roam; What once in midnight to the machine was wept May wake exposed beneath another dome. Use well this tool, but guard thy inmost part; Trust not the mirror more than thine own heart.

Gonzalo Lerena yes, usually... and we don’t want to wear out that welcome... My bot Buddy will always listen to me... without getting offended or woken up

On-premise AI for critical infrastructure just got a lot more compelling. No cloud dependency, no latency, no data sovereignty risk. This is the hardware story that makes what we’re building at Utilyst inevitable. 💧

This will make for a compelling addition with some of the work we're doing in the AI appliance space. Empowering organizations with meaningful AI workflows on-prem can lead to meaningful reduction in the majority of their cloud spend.

How much it costs? In-house solution is for poor))) tell me how much it costs?

Sure it will be added advantage if we learn how to use it

Should be illegal to give it all this value for free😅 Thanks mahn🤍🫡

Thats 200B model on Q4 Quantisation not FP16

Great resources

Azeem Ullah

This is an interesting shift in thinking, especially moving from single large models to coordinated ensembles. If the efficiency gains are real, it could meaningfully change how people approach compute heavy AI systems. The emphasis on voice nuance and context is a real gap in current systems, so that focus makes sense.

I need one of this OMG

I simplified checking open port on linux: please watch and share :

Github repos are now the hidden gold mines. Alot of resources lie in there, which people don't know

I'm not sure about how practical this mini PC would be to train any AI models, especially in terms of cooling during time-consuming AI model training processes. It might only survive as a thin client.

Cuda is the problem

I completed my master's degree in Mass communication and journalism, not yet get job, please let reference me

Thank you for sharing ✨️

Thank you for sharing

Daniel Uhlemann my mac m1 ultra has similar specs. Might not be as fast but i had it for 5 years b