Viewing profile — universesquid

MCP is very easy to use because it allows to just dump it in the model api call and the providers handle the calling. A bit easier than running the tool call loop

https://github.com/advisories/GHSA-8mgj-vmr8-frr6

cool thanks for that comment, I might update this in a couple weeks time since it seems to interest people but general feedback that it's too shallow. Wanted to give some high leve…

1.) technically yes, most models used for that task are NLP but not LLMs in the modern sense though 2.) Actually they don't. Multimodal LLMs parse PDFs by taking multiple screensho…

Hey everyone, is your company using a fine-tuned Open Source Model instead of OpenAI products for production tasks or thinking about it? How are your experiences with that?

It's really a shocker to me whenever I see people in obviously difficult situations worry about their productivity. Like is this really what modern life has become? Build whole ide…

Hey everyone, I am super interested to learn more about challenges you faced when building and deploying applications with langchain. Some questions that I had while building a sma…

Hey everyone, I am trying to figure out how DevOps requirements change with services that build on top of LLMs. I got a couple questions for everyone who actually tried to deploy s…