The Go-to Language for AI: Opportunities and Challenges
summary
Claims that Go can run local LLM stacks with spago and localAI drive the talk, showing pure-Go NLP: token classification, zero-shot classification, question answering and named entity recognition running in milliseconds. Examples include loading Hugging Face models locally (7B models cited), embeddings plus cosine similarity for search, and a cited ~$63M training cost for GPT‑4 with inference ~90% cheaper. Demos emphasize single‑executable, zero‑dependency deployments and tradeoffs versus C++/Rust GPU bindings.
AI-written summary · about
chapters (11)
- 0:00Introduction and context
- 2:26Understanding AI technology
- 3:59Deep learning mechanics
- 6:16Practical AI application
- 7:48AI tools and ecosystems
- 10:11AI development with Go
- 20:15Spago library overview
- 22:09Audio processing case study
- 22:35Live demonstrations
- 23:17Advanced NLP in Go
- 23:30Conclusion and Q&A
related talks
28mBuilding AI Applications in Go
43mAI and Go: Opportunities and Challenges Panel Discussion
28m(Neural) Natural Language Processing in Go
33mspaGO: a work-in-progress yet ready-to-use library for ML/NLP
01h 01mBuilding Generative AI Applications in Go- Gari Singh, Google (Part 1)
31mDecoding AI: A Go Programmer's Perspective
34mBuilding a Go AI with Kubernetes and TensorFlow
31mAI-Driven Development in Go