StarZero All shows Try the podcast clipper →

Beyang Liu

Co-founder & CTO, Sourcegraph · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

founderexecutiveengineer@beyang ↗LinkedIn ↗beyang.org ↗

He co-founded Sourcegraph in 2013 to build code search and intelligence infrastructure, overseeing technical architecture for tools such as Cody and Amp. Before founding Sourcegraph, he conducted machine learning and computer vision research at the Stanford AI Lab and worked as a software engineer at Palantir Technologies.

12statements → 5claims → 0claims resolved → 3.42/5average certainty → 2.58/5average debate potential → ≈4.5/5argument clarity, estimated → 4said about them ↓

5 not checkable as stated how the 5 claims stand · each chip opens the sources

3 predictions · 2 assertions · 3 opinions · 4 insights · every statement was checked. The predictions and assertions are the 5 claims: statements the public record can support or contradict. 0 are resolved, and 5 name no date, number or outcome precise enough to check. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Beyang argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

How they sound: not measured why? →

We measure speaking style by listening to the audio itself, and a fair number needs at least 2,000 words from one person on tape we have measured. There is too little of Beyang Liu on measured tape to publish a rate. This says nothing about how they speak.

Everything Beyang Liu said on Latent Space that made the record, most notable first. Filter by type, assessment or year in the ledger →

Assertion Not checkable as stated
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…”
Beyang Liu Dec 17, 2023 ▶ 15:22 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Opinion
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.”
Beyang Liu Dec 17, 2023 ▶ 24:08 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Prediction Not checkable as stated
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 …”
Beyang Liu Dec 17, 2023 ▶ 29:29 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Opinion
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.”
Beyang Liu Dec 17, 2023 ▶ 1:09:58 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Insight
Liu: Reliable single-step generation is a strict prerequisite for true AI agents
“If you want to get to the point where you can actually be truly agentic or like multi-step automated a necessary part of that is like the single step has to be robust and reliable.”
Beyang Liu Dec 17, 2023 ▶ 1:30:29 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Prediction Not checkable as stated
Liu: AI coding assistants must pull context beyond Git repositories to succeed
“And I don't think the AI developer will be any different. It will need to pull context from all these different sources.”
Beyang Liu Dec 17, 2023 ▶ 37:22 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Prediction Not checkable as stated
Liu: Post-hype reality check will expose the limits of AI search techniques
“And I don't know, I think in the next year or two, maybe as like the, as we get past like the peak AI hype, we'll start to see the gap emerge or become more obvious to more people about like how, how, how many of like the newfangled techniques actually work in…”
Beyang Liu Dec 17, 2023 ▶ 1:05:04 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Insight
Liu: Codebase complexity is software's bottleneck, not code generation speed
“The real problem of modern software development, I think is, is not how quickly can you write more lines of code. It's really about managing the emergent complexity of code bases as they evolve and grow, and how to get, how to make like efficient development t…”
Beyang Liu Dec 17, 2023 ▶ 1:15:26 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Assertion Not checkable as stated
Liu: No AI coding tool uses one model for completion and chat
“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.”
Beyang Liu Dec 17, 2023 ▶ 14:27 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Insight
Liu: Long-context recall depends directly on needle-in-haystack training loss
“The skill with which models are able to take advantage of context is always going to be dependent on how that factors into the impact on the training loss, right? So like, If you want long context window models to work well, then you have to have a ton of data…”
Beyang Liu Dec 17, 2023 ▶ 19:44 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Insight
Liu: Deterministic graph context eliminates common AI code completion type errors
“Turns out that works really well. Like, you can eliminate a lot of type errors that, that AI coding tools make just by pulling in that context.”
Beyang Liu Dec 17, 2023 ▶ 56:58 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
Opinion
Liu: Synthetic data and task-specific fine-tuning provide alpha for code automation
“I feel like most models today, they still use, like, combination of, like, the stack and the pile as, like their training corpus but you can only stretch that so far. At some point, we need more data and I don't know. I think there's still more alpha in, like,…”
Beyang Liu Dec 17, 2023 ▶ 1:11:39 The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph

The other half of the tape: Beyang Liu's own voice is left out of every number here. Other people bring the name up 4 times in 2 episodes on Latent Space. every mention, with the transcript →

Who brings them up most Alessio Fanelli 2Thorsten Ball 1Quinn Slack 1

Every mention by year

tap a year for its mentions
00213120252026episodesmentions
01120252026episodes it came up in
001.50.53120252026episodesmentions per episode
2026 1 mention in 1 episode
2025 3 mentions in 1 episode

Appearances (1)

EpisodeDateSpeaking time
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceG Dec 17, 2023 46m
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more