Liu: No AI coding tool uses one model for completion and chat
Beyang Liu · The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph · Dec 17, 2023 · at 14:27
Beyang Liu (CTO of Sourcegraph) discusses AI coding assistant architecture, explaining how latency requirements necessitate different models for inline completion versus chat.
0:00 / 0:06exact quote · 6.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Everyone uses a range of model. No, like, no one uses the same model for, like, inline completion versus, like, chat because the latency requirements were.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Beyang Liu
Liu: Cody matches GitHub Copilot completion acceptance rates using open-source StarCoder
“Like today, Cody uses StarCoder for inline completions, and with the benefit of the context that we provide, we actually show, like, comparable completion acceptance rate metrics. It's kind of like the standard metric that folks use to evaluate inline completi…”
Liu: Pure transformer models are insufficient to support autonomous AI agents
“We're actually a little bit, I think, more bearish than the average, you know, AI hypefluencer out there on the feasibility of agents with purely kind of like transformer-based models.”
Liu: Reliable AI coding workflows require search-based algorithmic backbones
“The way that we get to this, like, more reliable, multi-step workflows that can do things beyond, you know, generate unit test is, is, it's really gonna be, like, a search-based approach, where, where you use an LLM as, kind of, like, an advisor or a proposal …”
Liu: Open-source AI models are currently state-of-the-art for code completion
“Yeah, I mean, for completions, open source is, is state of the art right now.”