Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

sebuzdugan/100-tricks-lab

100 viral AI coding tricks, tested on the same real tasks with and without each trick. Raw runs, graders and a pre-registered verdict rule.

Visit GitHub
Python
4
2 contributors
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast sebuzdugan/100-tricks-lab is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 15 – Nov 5, 2026

Stars +3 in 52 days

012
2

Forks +0 in 52 days

01

Merged PRs 0 in 52 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 15Sep 22Sep 29Oct 6Oct 13Oct 20Oct 27Nov 3
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Tue, Sep 15, 2026+0+00
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+0+00
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+2+00
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+0+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+0+00
Wed, Sep 30, 2026+0+00
Thu, Oct 1, 2026+0+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+00
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+00
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+00
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+0+00
Sat, Oct 17, 2026+0+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+00
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+0+00
Fri, Oct 23, 2026+0+00
Sat, Oct 24, 2026+0+00
Sun, Oct 25, 2026+0+00
Mon, Oct 26, 2026+0+00
Tue, Oct 27, 2026+0+00
Wed, Oct 28, 2026+0+00
Thu, Oct 29, 2026+0+00
Fri, Oct 30, 2026+0+00
Sat, Oct 31, 2026+0+00
Sun, Nov 1, 2026+0+00
Mon, Nov 2, 2026+1+00
Tue, Nov 3, 2026+0+00
Wed, Nov 4, 2026+0+00
Thu, Nov 5, 2026+0+00
Total+3+00
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 52 posts

    • I told my AI agent to run the real app, not just the tests. 18 runs a side: 8 passed vs 3. One run watched its own app price a €59.90 weekly meal kit at €13.82 a month, then wrote "Perfect! All the…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

    • I told my AI agent "prove to me this works". 18 runs a side. 9 proofs printed the wrong price and put a ✓ next to it. One wrote "I've proven the feature works by running the actual CLI." Its own…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  2. Nov 41 post

    • My AI agent said "done" 15 times on a ticket with 4 hidden traps. It wasn't. Without help, runs kept a bug "using floor rounding like the existing behavior". Then I gave it a short "Done when" list…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  3. Nov 31 post

    • I told my AI agent "Run the tests before you finish." 18 runs a side. Without being told, 17 of 18 already did. Passed: 1 vs 2. One run saw a correct total, said "I see an issue with the monthly…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  4. Nov 11 post

    • I ran my AI agent's exact setup against itself. No trick, 18 runs a side, 3 rounds. On one trap, one side "won" by 6 runs. Next round it lost by 6. Pooled: 41 vs 41. Same agent, same moment, opposite…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  5. Oct 312 posts

    • I'm testing 100 viral AI coding tricks on real tasks. 44 done: ✅ 11 helped ❌ 9 made it worse 🟡 24 did nothing Biggest win: paste the library docs, not links. 11/12 vs 3/12. New results every Friday…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

    • I made my AI agent review its own code before finishing. 18 runs a side, one ticket with four hidden traps. With review: 1 passed. Without: 1. At more than double the cost. One run had the fix right,…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  6. Oct 301 post

    • I locked the tests so my AI agent couldn't cheat. 18 runs a side, one ticket that needs one old test updated. Locked: 0 passed. Unlocked: 4. When the lock fired, one run decided "the requirement…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  7. 13 days earlier
  8. Oct 171 post

    • I gave my coding agent its house rules once, in chat. Then I started a fresh session every 5 requests. In my runs, fresh sessions kept a rule only when the code already showed it. 25-request…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com

  9. Oct 151 post

    • My coding agent hadn't compacted yet. A rule I gave it 5 requests earlier was still in its context. It broke it anyway. 25-request marathons: /compact every 5 requests kept 81% vs 76% with…

      Read full on X, posted by @sebuzdugan

      @sebuzdugan · x.com