DEV Community

DEV Challenges

This is the official tag for submissions and announcements related to DEV Challenges.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
🌊 Ripple — Turn Community Needs Into Action

🌊 Ripple — Turn Community Needs Into Action

2
Comments
2 min read
FinePrint: an agent that checks your hackathon entry against the rules it reads

Sanity Challenge Path One Submission

FinePrint: an agent that checks your hackathon entry against the rules it reads

29
Comments 4
11 min read
An AI Correctly Ignored a Forum Rumor. I Removed One Label and It Paid Out $150.

Kaggle Benchmarking Challenge Submission

An AI Correctly Ignored a Forum Rumor. I Removed One Label and It Paid Out $150.

5
Comments 4
7 min read
10 Real Airflow Incidents, 5 AI Models — Which One Handled Production Best?

Kaggle Benchmarking Challenge Submission

10 Real Airflow Incidents, 5 AI Models — Which One Handled Production Best?

Comments 2
4 min read
INKSHIFT: cross out a table, keep the booking

Sanity Challenge Path Two Submission

INKSHIFT: cross out a table, keep the booking

24
Comments 1
10 min read
Join the Kaggle Benchmarking Challenge: $2,500 in Prizes for FIVE Winners!

Open-ended scope for custom model testing

Join the Kaggle Benchmarking Challenge: $2,500 in Prizes for FIVE Winners!

205
Comments 76
4 min read
UMKM-Bench: I tested 8 LLMs on how Indonesians really text online shops

Kaggle Benchmarking Challenge Submission

UMKM-Bench: I tested 8 LLMs on how Indonesians really text online shops

1
Comments 6
8 min read
Beyond the Prompt: Why the Hermes Agent Is the Self-Improving AI We Actually Needed

Hermes Agent Challenge Submission: Write About Hermes Agent

Beyond the Prompt: Why the Hermes Agent Is the Self-Improving AI We Actually Needed

5
Comments
2 min read
Honest Associate: a legal research agent that structurally cannot cite a fake case

Sanity Challenge Path One Submission

Honest Associate: a legal research agent that structurally cannot cite a fake case

1
Comments
6 min read
OmniML: We Built an AutoML System That Refuses to Be a Black Box

OmniML: We Built an AutoML System That Refuses to Be a Black Box

20
Picked as gem Comments 4
7 min read
My screener recommended every job it could not read

Summer Bug Smash: Clear the Lineup 🐛🛹

My screener recommended every job it could not read

1
Comments
4 min read
# **Titanic – Machine Learning From Disaster: A Complete Project Overview**

Kaggle Benchmarking Challenge Submission

# **Titanic – Machine Learning From Disaster: A Complete Project Overview**

1
Comments 1
4 min read
When Judge Bias Matters More Than Eligibility: The Hidden Problem With Modern Hackathons

When Judge Bias Matters More Than Eligibility: The Hidden Problem With Modern Hackathons

6
Comments 2
7 min read
Sanity's Knowledge Base stopped 6 of 7 poisoned pages. The 7th fooled Claude Opus 5.

Sanity Challenge Path One Submission

Sanity's Knowledge Base stopped 6 of 7 poisoned pages. The 7th fooled Claude Opus 5.

5
Comments 2
7 min read
The page with the answer was missing. Half the models added up a total the document never states.

Kaggle Benchmarking Challenge Submission

The page with the answer was missing. Half the models added up a total the document never states.

Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.