universeodon.com is part of the decentralized social network powered by Mastodon.
Be one with the #fediverse. Join millions of humans building, creating, and collaborating on Mastodon Social Network. Supports 1000 character posts.

Administered by:

Server stats:

4.1K
active users

Learn more

#openai

367 posts257 participants2 posts today

I am doing a lot of testing with various LLMs, either locally run, deploying serverless on Runpod.io, or with APIs, and I gotta say the best experience I've had so far is gpt4o-mini. I've been hammering it with tests in n8n this past week and have only racked up $0.02, which makes it great for learning how to integrate LLMs into external applications.

#ai#llm#n8n

"The whole point of hiring a researcher is that you can rely on their research, that they're doing work for you that would otherwise take you hours. Deep Research is the AI slop of academia — low-quality research-slop built for people that don't really care about quality or substance, and it’s not immediately obvious who it’s for.

Surely, if you’re engaged enough to spend $200 on an OpenAI subscription and are aware of Deep Research, you probably know what SEO bait is, and can distinguish between low-quality and high-quality content. If you were presented with a document with such low-quality, repetitive citations, you’d shred it — and, if created by an intern, you’d shred them too. Or, at the very least, give them some stern words of guidance.

Let me put this in very blunt terms: we are more than two years into the generative AI boom and OpenAI's biggest, sexiest products are Deep Research — a product that dares to ask "what if you were able to spend a lot of compute to get a poorly-cited research paper," and Operator, a compute-intensive application that rarely completes a task in minutes that would otherwise have taken you seconds."

wheresyoured.at/longcon/

Ed Zitron's Where's Your Ed At · The Generative AI ConIt's been just over two years and two months since ChatGPT launched, and in that time we've seen Large Language Models (LLMs) blossom from a novel concept into one of the most craven cons of the 21st century — a cynical bubble inflated by OpenAI CEO Sam Altman built to sell