What We've Learned From A Year of Building with LLMs
From the tactical nuts & bolts to the operational day-to-day to the long-term business strategy.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
From the tactical nuts & bolts to the operational day-to-day to the long-term business strategy.
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.
Introduction At Replit, we are rethinking the developer experience with AI as a first-class citizen of the development environment. Towards this vision, we are tightly integrating AI tools with our IDE. Currently, LLMs specialized for programming are trained with a mixture of…
Salesforce integrates OpenAI’s enterprise-ready LLMs to transform customer applications.
This post walks through how you could incorporate a local LLM using Ollama in Obsidian, or potentially any note taking tool.
Distinguishing problems with external vs. internal LLMs, and data vs non-data patterns
Anthropic describes Constitutional AI method: training LLMs with explicit principles for safer, more controllable outputs.
It started with a question that had no clear answer, and led to eight PRs from the community.
Should chat be the main UX for LLMs? I don't think so and believe we can do better.
Also, shortcomings in document retrieval and how to overcome them with search & recsys techniques.
Asking LLMs to generate biographies to get a sense of how they memorize and regurgitate.