Lance Martin ✓

@RLanceMartin · San Francisco, CA · joined 11 May 2009

MTS @anthropicai

38 369Followers

466Following

1 386Posts total

1MViews on collected posts

Against accounts of the same size

7 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views62 656this account2 896median for 10K–100K

Reach, %163.30%this account9.51%median for 10K–100K

Engagement, %0.77%this account1.56%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	62 656	2 896	21.6×
Reach (views ÷ followers)	163.30%	9.51%	17.2×
Engagement rate	0.77%	1.56%	0.49×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

11.8K21 Jul

14.5K24 Jul

403.1K25 Jul

26.4K26 Jul

143.3K1 Sep

365.8K2 Sep

62.7K

Last 7 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.67%21 Jul

1.29%24 Jul

0.60%25 Jul

0.49%26 Jul

1.10%1 Sep

1.25%2 Sep

0.77%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.56%.

What the audience does

Likes70.6%8 434 in total

Reposts5.5%663 in total

Replies2.5%304 in total

Quotes0.5%61 in total

Bookmarks20.8%2 485 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

i recently added this command to the claude-api skill. run it in Claude Code to fix common prompting "anti-patterns" that can hobble frontier models: /claude-api prompt-audit patterns include: 1/Verification rituals. Instructions like "double-check your work” or "verify http 62.7K views · 404 likes · 29 reposts · 42 replies 02 Sep 2026 If you're trying out Fable 5.1 I highly recommend running: /claude-api prompt-audit on your skills. It finds a bunch of redundancies and rules to remove for the latest models. Running it for all my skills now. 365.8K views · 4.3K likes · 194 reposts · 98 replies 02 Sep 2026 some tips for Claude Fable 5.1 Try Fable 5.1 at low effort | Fable 5.1 at low effort is often competitive with Opus and Sonnet on $ / task while scoring higher. on CursorBench 3.2.0, Fable 5.1 at low effort is at parity w/ Fable 5 at high effort at a third of the cost. Prompt 143.3K views · 1.4K likes · 89 reposts · 70 replies 01 Sep 2026 lol this talk is from AIE 2024 (before I was at Anthropic). im glad graphs are cool (again)! 26.4K views · 106 likes · 9 reposts · 14 replies 26 Jul 2026 Anthropic engineer just released a 2-hour workshop on "Graph Engineering" for agentic systems: “80% of our engineers are using self-improving loops. Now everyone is building agentic graphs.” • 00:00 - Introduction to RAG & Graphs • 06:39 - Core of "Graph Engineering" (state 403.1K views · 2K likes · 317 reposts · 70 replies 25 Jul 2026 Opus 5 is a great model for async / long-horizon work. Check out my talk from @aiDotEngineer on a few useful patterns : 1) split the brain + hands, 2) self-correction loops, 3) memory with dreaming, 4) org-level agent harnesses. https://t.co/aIEkU29y1C 14.5K views · 162 likes · 19 reposts · 6 replies 24 Jul 2026 this is a nice talk from Vercel Ship 2026. Harrison (a core contributor on Claude Managed Agents) covers some of the benefits of splitting the "brain" (agent harness) from the "hands" (@vercel sandboxes inside your VPC): https://t.co/Ep7Hxcoieo 11.8K views · 68 likes · 6 reposts · 4 replies 21 Jul 2026