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

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Bifrost
Bifrost

sophicle/cues

Code for Base Models Can Reason by Taking a Cue From Training Data

Visit GitHub
Python
43
6
1 contributors
MIT License
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Momentum

How fast sophicle/cues 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 5 – Oct 26, 2026

Stars +40 in 22 days

01020
18

Forks +6 in 22 days

0123
3

Merged PRs 0 in 22 days

01

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

Not in the Trendshift top 25 in this period

Oct 5Oct 8Oct 11Oct 14Oct 17Oct 20Oct 23Oct 26
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
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+1+00
Wed, Oct 7, 2026+4+00
Thu, Oct 8, 2026+18+30
Fri, Oct 9, 2026+1+10
Sat, Oct 10, 2026+1+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+2+10
Tue, Oct 13, 2026+2+00
Wed, Oct 14, 2026+1+00
Thu, Oct 15, 2026+1+00
Fri, Oct 16, 2026+2+00
Sat, Oct 17, 2026+1+10
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+1+00
Tue, Oct 20, 2026+1+00
Wed, Oct 21, 2026+0+00
Thu, Oct 22, 2026+2+00
Fri, Oct 23, 2026+2+00
Sat, Oct 24, 2026+0+00
Sun, Oct 25, 2026+0+00
Mon, Oct 26, 2026+0+00
Total+40+60
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 71 post
    • Swap every "okay" in a model's mid-training data for "chicken," and starting its answer with "Chicken" makes it solve the math problem and check its own work, about as well as "Okay" does. Before the…

      Read full on X, posted by @GptMaestro

      @GptMaestro · x.com

  2. Oct 62 posts
    • RL-Zero on Olmo-3-7B mostly changed the first two tokens of each answer. A new paper from Wang, Dravid, Shao, Farhat, Min and Efros compares the base model and its RL-trained version on identical…

      Read full on X, posted by @neuralloot

      @neuralloot · x.com

    • Analyzing the geometry of the GRPO weight update reveals that it aligns with directions that increase the probability of cue-related tokens, such as “Okay” and paragraph breaks. In fact, a…

      Read full on X, posted by @_AmilDravid

      @_AmilDravid · x.com

You might also like

Repositories close to sophicle/cues
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

yingfan-bot/lotus

Python

Code for Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers (https://arxiv.org/abs/2606.31779)

537

EleutherAI/math-lm

Python
1.1k97

GAIR-NLP/LIMO

Python

[COLM 2025] LIMO: Less is More for Reasoning

1.1k56

open-thoughts/open-thoughts

Python

Fully open data curation for reasoning models

2.4k200

GENTEL-lab/Fold2Reason

Python

Official code for Fold2Reason: Enhancing general reasoning in language models through protein-structure post-training.

1098

THU-BPM/RLCSD

Python

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

1155

WeiboAI/VibeThinker

Python

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

1.6k124

RUCBM/LaSeR

Python

[ICLR 2026] Official repository for the paper "LaSeR: Reinforcement Learning with Last-Token Self-Rewarding"

373

Kwai-Klear/RLEP

Python

RL with Experience Replay

592