RLanceMartin Profile Banner
Lance Martin Profile
Lance Martin

@RLanceMartin

Followers
15K
Following
6K
Media
417
Statuses
1K

langchain. past: robots 🚘 🤖, phd @stanford 🧪

San Francisco, CA
Joined May 2009
Don't wanna be here? Send us removal request.
@RLanceMartin
Lance Martin
10 days
Short video, too:.
0
1
2
@RLanceMartin
Lance Martin
10 days
Common “context engineering” patterns. Loved @dbreunig posts on this. I also wrote up some thoughts:.
Tweet media one
@dbreunig
Drew Breunig
20 days
As your context bloats, you hit different failure modes. These failures hit agents hardest because they operate in exactly the scenarios where contexts balloon: gathering information, making sequential tool calls, engaging in multi-turn reasoning, & accumulating histories.
Tweet media one
3
7
28
@RLanceMartin
Lance Martin
12 days
Code:.Longer vid:.
0
0
2
@RLanceMartin
Lance Martin
12 days
Gemini2.5 video understanding + text-to-speech are very good. Simple multi-modal researcher I put together using native web search + YouTube video understanding tools w/ text-to-speech. Researches topic + analyzes videos, produces report + custom podcast.
2
4
26
@RLanceMartin
Lance Martin
17 days
Code:.Course link:.
0
1
18
@RLanceMartin
Lance Martin
17 days
Building Async ("Ambient") Agents. Happy to share new, free course on building "ambient" agents! This is one of the most interesting agent UX patterns (e.g., Devin, Codex), allowing the agent to do work "in the background" and interact with the user via human-in-the-loop for
Tweet media one
5
62
364
@RLanceMartin
Lance Martin
19 days
Some useful references --.1/ @karpathy on LLMs as OS.2/ @walden_yan on context engineering.3/ @barry_zyj + team multi-agent.4/ @AymericRoucher + team on deep research.5/ @bcherny on.
1
6
34
@RLanceMartin
Lance Martin
19 days
I wrote about some popular patterns for managing context ("context engineering") w/ AI agents: .
Tweet media one
5
56
400
@RLanceMartin
Lance Martin
1 month
a few thoughts on the current state of agents based on what I saw at @aiDotEngineer: . rise of "ambient" agents. the bitter lesson & agent UX. RL for non-verifiable tasks. the case for MCP. early days for agent memory .
5
19
115
@RLanceMartin
Lance Martin
1 month
@kevinhou22 on Windsurf:.> Current dev workflow centric .> Highly opinionated UI / IDE.> Allows for granular data capture .> Lets them train models. @mntruell w/ @benthompson pod similar point; long “messy middle” of devs + AI working together preserves need for IDE.
0
0
6
@RLanceMartin
Lance Martin
1 month
Most interesting AI product question I took from @aiDotEngineer is Claude Code vs IDEs (Cursor/Windsurf). @bcherny on Claude Code: .> Bitter lesson centric .> General models win.> General things around model win.> Unopionionated / no UI.> Work w fast changing UX / models
2
1
39
@RLanceMartin
Lance Martin
1 month
Some notes from @aiDotEngineer day 1 -. @simonw on state of AI.> Visual eval for LLMs: asked each LLM to generate code for an SVG image of a pelican riding a bicycle. Ran this across ~30 model releases over the past 6 months. Created a script to select random image pairs, GPT4.1.
5
19
114
@RLanceMartin
Lance Martin
2 months
How @AnthropicAI is thinking abt memory.
Tweet media one
1
4
15
@RLanceMartin
Lance Martin
2 months
Agent can be hooked into Gmail by swapping out the tools used. Components are also general and can be used w/ various tools / MCP servers.
0
0
2
@RLanceMartin
Lance Martin
2 months
Memory -- Add memory, so the agent learned email response preferences from human feedback. Notebook:.
Tweet media one
1
0
5
@RLanceMartin
Lance Martin
2 months
Human-in-the-loop -- Add human in the loop for approval / editing of specific tool calls. Notebook:.
Tweet media one
1
0
2
@RLanceMartin
Lance Martin
2 months
Agent evals -- Unit tests (Pytest) for triage decision + tools calls (test structured outputs using heuristic eval) and LLM-as-judge to eval email responses. Notebook:.Slides:.
Tweet media one
2
0
5
@RLanceMartin
Lance Martin
2 months
Building agents -- Combing workflow (router) with agent that can call email tools. Notebook:.Slides:.
Tweet media one
1
0
2
@RLanceMartin
Lance Martin
2 months
Fundamentals -- Tool calling, agents v workflows (h/t @barry_zyj, @ErikSchluntz), persistence/checkpointing. Notebook:.Slides:
Tweet media one
1
1
8
@RLanceMartin
Lance Martin
2 months
Agents from scratch. This repo covers the basics of building agents:. Fundamentals . Build an agent. Agent eval. Agent w/ human-in-the-loop. Agent w/ long-term memory. Builds to a deployable agent to run your email. Code (all open source):.
Tweet media one
9
109
706