AI Assistant Behind the Firewall: Keeping the LLM + Frontend = Velocity Formula Without Exposing Code
summary
How to speed up frontend development using large language models while minimizing data-leak risks by deploying models behind a firewall. Covers LLM capabilities and limits, options for running models on private servers, and a practical team case showing how to integrate an on-premise AI assistant into frontend workflows without exposing source code.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 6:50LLM security issues
- 9:17Deploying LLM in-house
- 14:56LLM types and optimization
- 17:51Running LLM on laptop
- 20:58Demo of local LLM
- 27:06Fine-tuning local models
- 29:15Future of local LLM
- 30:38Q&A
related talks
09mIntegrating LLMs into Front-End Apps for Enhanced UX
28mNavigating LLM deployment: Tips, tricks, and techniques
06mData Privacy Concerns and Solutions When using LLMs in Production
47mA Step-by-Step Guide to Securing Large Language Models (LLMs)
25mBuilding Your own AI Assistant with JavaScript, LLMs, and Rag
26mAI-powered Productivity using Open-Source LLMs
25mSafeguarding Sensitive Data in the Age of Generative AI
51mInternal AI solutions -from hype to production