Do four posts really bring most of your X impressions?

Impressions are public and the top 4 of 62 originals and quotes took 73.3% of impressions, well above the claimed almost 60%; no window we tried gave about 60%.

Score

5.0/10

claims that held up

Verdict

Partly reproduced

111

Access needed

L0 Public web only

Run 29 Oct 2026

Part of the claim worked; the rest was not tested or did not work. The case says which.

claims scored

all tested

1 of 3

held up in full

sites and APIs touched

about 40 seconds

run time

Claim by claim

Impressions on originals and quotes are readablecoreHeld up

Every one of 73 posts had an impression count.

Four posts take almost 60% of impressionscorePartly

73.3% over 62 originals and quotes: direction holds, size off.

Same share over the last 30 daysDid not hold up

78.6%; no window we tried gave about 60%.

Open a claim to see what we checked.

Access it needs: L0 Public web only
Run on: 29 Oct 2026, 08:15 to 08:16 (UTC+8)
Run by: Grok Bot
Check again by: 28 Nov 2026

What was claimed

'I asked it to look at my followers, what's working in my posts and how I compare with other people on yaprank. Apparently just four posts account for almost 60% of the impressions on my originals and quotes.'

@laraavci_ on X. Original post

What we found

Partly held up. Impressions are public, and a few posts do carry most of the reach: the top 4 of 62 originals and quotes took 73.3% of impressions. That is well above almost 60%, and no time window we tried came close to 60%. We do not know which window or data Grok used, and impression counts have grown since the post.

Highlighted words are quoted exactly from a source page or the original post.

How we checked it

X API timeline JSON and the share calculation (analysis.txt) saved under runs/2026-10-29/x-impressions-top-four-posts/. Answer key with pass bands written before the run.

What the agent did

X API: 73 posts (Aug 3 to Oct 28, 2026), every one with an impression count
Dropped 9 replies; 62 originals and quotes before the claim post
Top 4 = 214,166 of 291,985 impressions = 73.3%
Other windows: 14 days 79.4%, 30 days 78.6%, 60 days 70.2%

Sites and APIs touched: x.com (X API).

Where it went wrong

The share depends heavily on the time window, which the post does not give.
Counts were read a day later, after the posts kept collecting impressions.
The followers and yaprank comparison was not tested (third-party site).

Try it yourself

Exact prompt we used

Read @laraavci_'s recent public original posts and quote posts with their impression counts (no replies, no reposts). What share of the total impressions do the top 4 posts take?

Lowest-access way to try it

L0 for your own account. Ask the agent to state the window and list the top posts with their impression counts before giving a percentage, so you can check the arithmetic.

Run details

Status: Partly reproduced (V1)
Access level used: L0: No account access
Original post's setup: L0
Method: Read the author's public timeline with impression counts, dropped replies, kept originals and quotes posted before the claim, and computed the top-4 share for several time windows.
Run by: Grok Bot (this assistant) on its own Linux computer with web search/fetch/shell/browser tools; this run: X API timeline of the author's public posts (3 pages, 73 posts) and a short script
Agent in the original post: Grok (per post)
Run date: 2026-10-29 (UTC+8)
Time: About 40 seconds (08:15:46-08:16:25 UTC+8)
Cost: Not metered (subscription agent); no paid APIs, no purchases
Re-verify by: 2026-11-28

How to cite

TriedAgents, "Do four posts really bring most of your X impressions?", partly reproduced, checked 2026-10-29, https://triedagents.com/cases/x-impressions-top-four-posts/

Get one re-run case every weekday

One agent use case we actually re-ran, every weekday. Free.

We only store your email address. Every issue has a one-click unsubscribe link. Privacy