Hacker Newsnew | past | comments | ask | show | jobs | submit | newusertoday's commentslogin

can you point some if you remember off the head? is it something like pipedream, n8n?

openai's AGI would be like FSD of tesla.


hey sama has trained under the best of charlatans...


this is great. I miss extensions in android browser. That existing extensions from web store would work out of the box is cherry on top.


agreed. There is no way to tell if someone is aware or not we rely on brain activity to say someone is alive or not there is no way to tell someone or something is conscious currently.


i generally use plantuml in emacs for generating diagrams from text but it does not allows for drag and drop editing. This looks cool.


not working says deployment not found


why does ollama engine has to change to support new models? every time a new model comes ollama has to be upgraded.


Because of things like this: https://github.com/ggml-org/llama.cpp/issues/12637

Where "supporting" a model doesn't mean what you think it means for cpp

Between that and the long saga with vision models having only partial support, with a CLI tool, and no llama-server support (they only fixed all that very recently) the fact of the matter is that ollama is moving faster and implementing what people want before lama.cpp now

And it will finally shut down all the people who kept copy pasting the same criticism of ollama "it's just a llama.cpp wrapper why are you not using cpp instead"


There's also some interpersonal conflict in llama.cpp that's hampering other bug fixes https://github.com/ikawrakow/ik_llama.cpp/pull/400


What the hell is going on there? It’s utterly bizarre to see devs discussing granting each other licences to work on the same code for an open source project. How on earth did they end up there?


There seems to be some bad blood between ikawrakow and ggerganov: https://github.com/ikawrakow/ik_llama.cpp/discussions/316


But he's talking about a MIT License!

WTF


My guess is that there's money involved. Maybe a spat between an ex-employee and their ex-employer?


Now it’s just a wrapper around hosted APIs.

Went with my own wrapper around llama.cpp and stable-diffusion.cpp with optional prompting hosted if I don’t like the result so much, but it makes a good start for hosted to improve on.

Also obfuscates any requests sent to hosted, cause why feed them insight to my use case when I just want to double check algorithmic choices of local AI? The ground truth relationship func names and variable names imply is my little secret


Wait, what hosted APIs is Ollama wrapping?


very nice demo. I saw that you are using threejs but when i checked network logs its not downloading it which is great. Are you doing SSR?


Thank you. I am using https://globe.gl/ which wraps three.js. The page realtime page is still pretty slow to load so though.

I'm using Next.js but I'm using all client-side components. The tooling around SPA client side state is just really good so I don't see a huge reason to go full SSR, especially when SEO doesn't matter for the actual app.


water, look at indus water treaty for more details. As per last report it is in abeyance neither suspended nor terminated. Not sure what it means.


very nice. I wanted something like this for Parquet but couldn't find one, this one looks great.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: