Prediction Didn’t hold up AI assessment confidence: 95% certainty 3/5 debate potential 2/5

Byung Liu: Sourcegraph will offer a self-hostable LLM within six months

Byung Liu · Embedded AI: The Questions Every CEO is Asking · Jun 2, 2023 · at 32:22

Byung Liu of Sourcegraph discusses enterprise data privacy concerns and the company's timeline for providing self-hostable language models to clients.

0:00 / 0:14exact quote · 14.2s

▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark

“And while we don't have one that's like completely self-hostable yet, I think, you know, with all the interesting things happening around, you know, llama, alpaca and that sort of thing, I think like within six months we'll, we'll have like a viable language model that can do like really good Q and A based interactions.”

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 →

The claim, plainly

Sourcegraph will release a viable, fully self-hostable language model for Q&A interactions within six months.

a quote alone can be ambiguous, so this restates it with the references and context of the conversation around it resolved. AI-written; the tape below the player is the source.

Assessment

By the December 2, 2023 deadline, Sourcegraph had not released a fully self-hostable language model for Q&A interactions. While Sourcegraph allowed enterprise customers to self-host the core Sourcegraph platform and route requests to private cloud LLM endpoints (such as Azure OpenAI or AWS Bedrock), all Q&A and chat interactions in Cody continued to rely on cloud-hosted third-party model APIs rather than a native self-hostable language model provided by Sourcegraph.

Sourcegraph product updates up to December 2, 2023 show Q&A and chat features relied entirely on external cloud-hosted LLM APIs (such as Anthropic Claude and OpenAI models).
Sourcegraph's October 31, 2023 technical blog post confirmed that Cody's Q&A capabilities were powered by cloud-connected LLM APIs rather than a self-hostable model.
By the stated horizon date of December 2, 2023, no product announcement, blog post, or official documentation was released showing a self-hostable Q&A model.

Checked against

[1] sourcegraph.com [2] sourcegraph.com [3] dev.to [4] sourcegraph.com [5] sourcegraph.com [6] sourcegraph.com [7] sourcegraph.com [8] sourcegraph.com

Sourcegraph Cody local model self hostable 2023 site:sourcegraph.com "StarCoder" 2023 Sourcegraph Cody self hosted LLM release December 2023 Sourcegraph Cody self hosted language model 2023 "Local code completion with Ollama and Cody" sourcegraph

assessed as of 2026-07-28

This assessment is an AI reading of a public statement, made against the cited references with the confidence shown. It can be wrong. The quote, the tape and the references are all on this page; if something is off, use report an error below. full disclaimer →

Mentioned

Alpaca Llama Sourcegraph

⚑ Spot an error? Report it

More from Byung Liu

Assertion Not checkable as stated

Byung Liu: Sourcegraph's Cody is the only AI fetching full codebase context

“As far as I know, Cody is, is the only AI enabled editor assistant or coding tool today that, that fetches context as kind of like as broadly as we do.”

Byung Liu Jun 2, 2023 ▶ 16:36 Embedded AI: The Questions Every CEO is Asking

Insight

Byung Liu: LLMs increase search engine value instead of replacing them

“It is not true that language models make search engines unnecessary. If anything, they make the search engines more valuable because now all that data that you can search Becomes like 10 x more powerful because you can use that to, you know, get to get to your…”

Byung Liu Jun 2, 2023 ▶ 36:40 Embedded AI: The Questions Every CEO is Asking

Insight

Byung Liu: LLM output quality depends primarily on provided context

“Context is king. So the context that you provide to a language model really dictates the quality of the output of the model, especially if you're asking about things that are kind of outside the training corpus of that model.”

Byung Liu Jun 2, 2023 ▶ 14:01 Embedded AI: The Questions Every CEO is Asking

Assertion Partly supported

Byung Liu: Sourcegraph's code graph achieves compiler-level accuracy across languages

“Like that's the code graph that we spent the past 10 years building. And we can do that essentially in any language, any code base at compiler level accuracy.”

Byung Liu Jun 2, 2023 ▶ 18:04 Embedded AI: The Questions Every CEO is Asking

Byung Liu: Sourcegraph will offer a self-hostable LLM within six months

More from Byung Liu

Turn any episode into a week of clips.