Lance Martin

6 statements across 1 episodes · 2 bullish · 2 bearish · 1 people on the record · first statement Sep 11, 2025 by Lance Martin · said 1 times in 1 episodes since 2025 · across every show →

On the record as a speaker too: Lance Martin's record, appearances and statements → this page counts the times other people say the name.

Mentions by year

brought up most by Shawn Wang (1)

tap a year for its mentions
0011112025episodesmentions
0112025episodes it came up in
000.50.5112025episodesmentions per episode
2025 1 mention in 1 episode

every mention, scene by scene, with the transcript →

Everything said about Lance Martin, oldest first

Sep 11, 2025 positive
Insight
Martin: The best open-source strategy pairs building tools with educational on-ramps
“I like this one, two punch of building a thing like open deep research, then creating a class so people can actually understand how to build it themselves. And I kind of like that build a thing, create an on-ramp for it.”
Lance Martin Sep 11, 2025 ▶ 1:02:30 Context Engineering for Agents - Lance Martin, LangChain
Sep 11, 2025 negative
Insight
Lance Martin: Black-box agent abstractions break when underlying models evolve
“Agent abstractions are problematic because you don't know what's necessarily under the hood of the abstraction. You don't understand it. And if I was building, for example, you know, OpenDeep research with an abstraction, I wouldn't necessarily know how to rip…”
Lance Martin Sep 11, 2025 ▶ 58:22 Context Engineering for Agents - Lance Martin, LangChain
Sep 11, 2025 positive
Insight
Martin: Multi-agent systems excel at parallel read-only tasks, not writing tasks
“I like the take that apply multi-agents to problems that are easily parallelizable, that are read-only, for example, context gathering for deep research, and do, like, the final quote-unquote write, in this case report writing, at the end. I think this is tric…”
Lance Martin Sep 11, 2025 ▶ 14:54 Context Engineering for Agents - Lance Martin, LangChain
Sep 11, 2025 negative
Disclosure
Martin: A naive deep researcher loop consumed 500,000 tokens per run
“My deep researcher, for example, with the naive tool calling loop was using 500,000 tokens. It was like a dollar to two dollars per run.”
Lance Martin Sep 11, 2025 ▶ 3:56 Context Engineering for Agents - Lance Martin, LangChain
Sep 11, 2025 neutral
Insight
Lance Martin: Prompt engineering is a subset of context engineering
“Well, I think that, you know, prompt engineering is kind of a subset of context engineering.”
Lance Martin Sep 11, 2025 ▶ 2:25 Context Engineering for Agents - Lance Martin, LangChain
Sep 11, 2025 neutral
Assertion Supported
Martin: Anthropic uses parallel sub-agents for research and single-shot final writing
“Anthropic reported on this too. So their deep researcher just uses parallelized subagents for research collation, and they do the writing in one shot at the end.”
Lance Martin Sep 11, 2025 ▶ 13:50 Context Engineering for Agents - Lance Martin, LangChain
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.