Harry Tandy ✓

@HarryTandy · US, Florida · joined 13 Nov 2017

AI Researcher | Exploring Agentic Workflows | Follow for daily AI insights

23 344Followers

1 959Following

27 633Posts total

153.1KViews on collected posts

Against accounts of the same size

9 posts from the last 90 days, next to the 10K–100K follower range. below its peers on both reach and engagement.

Median views770this account2 151median for 10K–100K

Reach, %3.30%this account6.48%median for 10K–100K

Engagement, %1.12%this account1.54%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	770	2 151	0.36×
Reach (views ÷ followers)	3.30%	6.48%	0.51×
Engagement rate	1.12%	1.54%	0.73×

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

141.2K11 Jun

411

267

1.1K

7K18 Aug

92631 Aug

770

7312 Sep

5823 Sep

Last 9 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.61%11 Jun

0.73%

1.12%

0.46%

0.51%18 Aug

3.13%31 Aug

2.21%

1.64%2 Sep

1.55%3 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.54%.

What the audience does

Likes29.1%793 in total

Reposts3.4%93 in total

Replies2.8%76 in total

Quotes0.4%11 in total

Bookmarks64.3%1 754 in total

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

Followers by day

4 Sep

Daily snapshots since 04 Sep 2026; the dashed line is the starting count.

Latest posts

NVIDIA robotics lead, Jim Fan: "We were born too late to explore the Earth and too early to travel the galaxies. But I believe we're born just in time to solve the physical Turing test" 20 minutes on world models, human data, simulation, and RL pushing robots toward https://t.c 582 views · 8 likes · 0 reposts · 1 replies 03 Sep 2026 I’d never let an agent ship code if its only proof was done Here’s the setup: > Task contract: spell out the finish line and the proof you expect > Safe workspace: isolate files, tools, and permissions > Independent checks: run tests, browser flows, and review agents & 731 views · 7 likes · 2 reposts · 3 replies 02 Sep 2026 A 50-minute JavaOne session with Vadim Briliantov, Technical Lead of Koog at JetBrains, turns a free-running agent loop into a typed execution graph. Briliantov builds it in code, adds a verifier branch, persists each graph step, and restarts from the exact node after a crash. h 770 views · 12 likes · 2 reposts · 3 replies 31 Aug 2026 This 61-minute session shows how product teams turn customer interviews into AI-assisted code, then move each change through small PRs, QA, and developer review. Lizzie Lawley, Head of Applied AI at Memrise and Founder and CEO of Wombat, walks through that workflow and shows htt 926 views · 14 likes · 5 reposts · 10 replies 31 Aug 2026 https://t.co/DmoQNcRlqk 7K views · 15 likes · 0 reposts · 13 replies 18 Aug 2026 @HarryTandy Learning everyday!! 1.1K views · 3 likes · 0 reposts · 2 replies 11 Jun 2026 @HarryTandy thanks for great tldr chad 267 views · 2 likes · 0 reposts · 1 replies 11 Jun 2026 @HarryTandy Very useful stage with Boris. Thanks for sharing Harry 411 views · 2 likes · 0 reposts · 1 replies 11 Jun 2026 Boris Cherny: "Overnight sub-agents do deeper work" 10-step Fable 5 setup you can copy this week: 1. Write CLAUDE.md - stack - commands - code style - forbidden files - review rules 2. Add PROJECT_MEMORY.md - verified facts - failed attempts - last session - next run 3. https 141.2K views · 730 likes · 84 reposts · 42 replies 11 Jun 2026