How Leidos Boosts Developer Efficiency With Llama
summary
Sourcegraph integrates an on‑premise Llama model into secure AWS environments to tackle large legacy codebases, replacing slow, stale open models with a low‑latency, up‑to‑date code assistant. Reported outcomes: 20% developer efficiency, 92% reduction in time lost to context switching and learning, and 33% faster feature implementation. The system provides code search, automated modernization, documentation generation and debugging automation, and shows measurable velocity gains for Leidos without cloud model latency or outdated training data.
AI-written summary · about
related talks
26mAI-powered Productivity using Open-Source LLMs
37mEmpowering Developers with local AI
01mSpeed Up Your Code With LLM's!
39mCombining the Best of Two Worlds: From TF-IDF to Llama LLM
27mBuilding Useful Apps With Small, Local LLMs
17mUnpacking the Llama Stack: Architecting Next-Gen AI Applications
49mNext-Gen Documentation with AI
44mAccelerating Software Development: The LLM (R)evolution