Guanlan Dai ✓

@guanlan

Building @Runta, the execution layer that controls what AI agents can actually do. Prev @Cloudflare and @Kong.

5 908Followers

480Following

343Posts total

359.7KViews on collected posts

Against accounts of the same size

5 posts from the last 90 days, next to the under 10K follower range. below its peers on both reach and engagement.

Median views18 132this account7 156median for under 10K

Reach, %306.91%this account505.37%median for under 10K

Engagement, %0.74%this account1.06%median for under 10K

Metric	This account	Median for under 10K	Ratio
Median views per post	18 132	7 156	2.53×
Reach (views ÷ followers)	3.1× audience	5.1× audience	0.61×
Engagement rate	0.74%	1.06%	0.70×

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

285.6K2 Sep

22.1K

18.1K

15.9K

17.9K

Last 5 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.86%2 Sep

0.74%

0.78%

0.36%

0.73%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.06%.

What the audience does

Likes50.5%2 414 in total

Reposts4.7%225 in total

Replies4.8%231 in total

Quotes1.7%83 in total

Bookmarks38.3%1 831 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

v1.0 focused on software engineering and terminal tasks. Next we will test the full harness × model grid. Much of what we observed points to harness-model fit rather than harness quality, and we want to identify which combinations maximize pass rates while minimizing cost. 17.9K views · 109 likes · 3 reposts · 16 replies 02 Sep 2026 Something we learned: With implicit prefix caching, running a task once during debugging leaves it warm for hours. Test a harness on Tuesday, benchmark it Wednesday, and it shows up cheaper than it should. Nothing in the logs tells you why. So no benchmark task was touched http 15.9K views · 53 likes · 0 reposts · 4 replies 02 Sep 2026 If you just want to know what to use: Codex if you don't want to think about it. Best pass rate, medium cost. Pi if the same job runs a thousand times and the bill adds up. Exo if retries are cheap and you'd rather it quit early than grind. DSH if you care about wall-clock and h 18.1K views · 130 likes · 7 reposts · 4 replies 02 Sep 2026 Here is the run that made us write this up. One of the hardest tasks, the pass rate (all model efforts) on DeepSWE is 38%, Pi and Claude Code both fixed it. Pi took 90 turns and $2.50. Claude Code took 381 turns and $64.36. Roughly 26x more for the same fix. https://t.co/VCX37w 22.1K views · 145 likes · 6 reposts · 9 replies 02 Sep 2026 A year ago the question was which model. Now it's which harness. Pi, Exo, Claude Code, Codex, DeepSeek Harness and 4 others. Same model, same tasks, same runtime. 360 runs, 2 billion tokens. Pass rates: 50% to 67%. Cost per pass: $1.05 to $18.34. Introducing FrontierHarness ht 285.6K views · 2K likes · 209 reposts · 198 replies 02 Sep 2026