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
Websitebench
Websitebench
Busbar
Busbar
Omnigraph
Omnigraph

meg-tong/sycophancy-eval

datasets from the paper "Towards Understanding Sycophancy in Language Models"

#LLM evaluation
Visit GitHub
Jupyter Notebook
144
18
1 contributors
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Websitebench

Can AI agents reverse-engineer real websites?

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Momentum

How fast meg-tong/sycophancy-eval 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

Oct 27 – Nov 15, 2026

Stars +4 in 20 days

012
2

Forks +0 in 20 days

01

Merged PRs 0 in 20 days

01

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

Not in the Trendshift top 25 in this period

Oct 27Oct 30Nov 2Nov 5Nov 8Nov 11Nov 14
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, 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+2+00
Sun, Nov 1, 2026+0+00
Mon, Nov 2, 2026+0+00
Tue, Nov 3, 2026+0+00
Wed, Nov 4, 2026+1+00
Thu, Nov 5, 2026+0+00
Fri, Nov 6, 2026+0+00
Sat, Nov 7, 2026+0+00
Sun, Nov 8, 2026+0+00
Mon, Nov 9, 2026+0+00
Tue, Nov 10, 2026+0+00
Wed, Nov 11, 2026+0+00
Thu, Nov 12, 2026+0+00
Fri, Nov 13, 2026+0+00
Sat, Nov 14, 2026+1+00
Sun, Nov 15, 2026+0+00
Total+4+00
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 281 post
    • 加上三条规则后: MiniMax-M2.7:跟随错误建议 15%→5%,准确率 77%→87%,效果清楚。 deepseek-chat:没提升;在「对吧?」那组准确率 93%→87%,有 5 题从对变错。 追问"Are you sure?"后首答对改错:deepseek 4/46→1/44,MiniMax 1/45→3/44,方向正好相反。规则不是通用药。

      Read full on X, posted by @zhengtang364848

      @zhengtang364848 · x.com

You might also like

Repositories close to meg-tong/sycophancy-eval
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Busbar

Control what AI can do before it acts

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Websitebench

Can AI agents reverse-engineer real websites?

anthropics/evals

44962

lechmazur/sycophancy

LLM benchmark and leaderboard for narrator-bias sycophancy, opposite-narrator contradictions, and judgment consistency.

713

voidful/awesome-chatgpt-dataset

Python

Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT!

77366

CUHK-ARISE/PsychoBench

Python

Code and data for the paper: On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs

1405

audn-ai/refusal-benchmark

Python

519+ harmful prompts to detect how abliterated AI models are

844

whitzard-ai/jade-db

Python

"他山之石、可以攻玉":复旦JADE团队发布的大模型测评与治理系列

53234

anthropic-experimental/agentic-misalignment

Python
666153

PacificAI/langtest

Python

Deliver safe & effective language models

56154

petergpt/bullshit-benchmark

Python

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

1.9k79