Speaking to AI Agents like Cavemen Saves 65% of Tokens. We Test.
A post on blog.jetbrains.com is cited by 8 distinct blogs to date (corpus.blog, measured 11 October 2026).
A record is what was published and who pointed at it. The text of the post is not shown here: read it at the source, or at its Wayback capture.
8blogs citing
| Period | Blogs | Links |
|---|---|---|
| All time | 8 | 8 |
| Last 90 days | 7 | 7 |
| Last 30 days | 3 | 3 |
| Last 7 days | 1 | 1 |
| First cited | 7 Jul 2026 |
|---|---|
| Latest citation | 7 Oct 2026 |
| Words blogs link it with | 5 |
| External links | 2 |
| Length | 953 |
1 this week (still settling) · peak 2
Show as table
| Week of | Value |
|---|---|
| 6 Jul 2026 | 1 |
| 13 Jul 2026 | 0 |
| 20 Jul 2026 | 1 |
| 27 Jul 2026 | 1 |
| 3 Aug 2026 | 1 |
| 10 Aug 2026 | 0 |
| 17 Aug 2026 | 0 |
| 24 Aug 2026 | 0 |
| 31 Aug 2026 | 1 |
| 7 Sept 2026 | 0 |
| 14 Sept 2026 | 0 |
| 21 Sept 2026 | 2 |
| 28 Sept 2026 | 0 (still settling) |
| 5 Oct 2026 | 1 (still settling) |
Each blog counts once, in the week of its first citation. A blog added to the index recently can bring old first citations in at once.
Words blogs link it with
The words blogs link this page with, by how many different blogs use them.
- across 82 paired skillsbench coding tasks, caveman cut output from the no-skill arm's 592,000 tokens to 542,0001 blog
- caveman prompting1 blog
- caveman test1 blog
- does speaking to agents like cavemen really save 65% of tokens? we test1 blog
- jetbrains evaluation1 blog
Cited by 8 blogs in 8 posts
One row per blog, the most recently citing first. Each shows the blog's newest citing post; open a row for the others.
linked as “JetBrains measured an 8.5% cut”
Read at paulsprogrammingnotes.com (opens in a new tab)linked as “Does Speaking to Agents Like Cavemen Really Save 65% of Tokens? We Test”
Read at keestalkstech.com (opens in a new tab)linked as “Caveman test”
Read at foojay.io (opens in a new tab)linked as “Across 82 paired SkillsBench coding tasks, Caveman cut output from the no-skill arm's 592,000 tokens…”
Read at jorypestorious.com (opens in a new tab)linked as “JetBrains evaluation”
Read at stuckinalocalminima.com (opens in a new tab)linked as “Caveman prompting”
Read at stet.sh (opens in a new tab)linked as “ran 86 real coding tasks”
Read at zernie.com (opens in a new tab)Links from this post
Elsewhere on blog.jetbrains.com (4)
Something wrong here? Report a problem