There has been a recent security breaches by Anthropic and OpenAI that they have problems in difficulty in working and handling with these advance AI models.
Comments URL: https://news.ycombinator.com/item?id=49123905
Points: 1
# Comments: 0
The list behind this ranks Boston Dynamics next to NVIDIA, Tesla, warehouse robots, and video analytics software, all under one label. A robotics foundation model and a SaaS tool running inference on a camera feed don't have much in common once you look at how they're built, but here they're in the same category. Worth knowing before you click: it's a blog, and the writers put themselves at the top of their own list. I do content distribution work for them, hence the disclosure. sub...
I open-sourced a multi-agent writing system. You give it a draft, and 6 agents work in sequence: analyze requirements, generate content, review quality, identify where diagrams belong, generate Draw.io XML, then inject diagrams back into the article. What makes it different from a ChatGPT wrapper: Agents are config-driven. Each agent's model, prompt, tools, and workflow are defined in YAML files, assembled at startup. Swapping an agent or adding a new one is a config change. It has mem...
Hello, I’m a disabled scholar who uses large language models (LLMs) to accommodate long-form scholarly writing. I’m writing to see if there are others out there doing the same so that we can develop a cohort or support community to share ideas and learn from each other’s mistakes. I realize that most of this group is coders and therefore won’t apply. That’s fine. I lurk here tho, so there might be others. Earl Gordon Barnett Earlgbarnett [at] gmail.com
