DEV Community

Kaggle Benchmarking Challenge

This is the official tag for submissions and announcements related to the Kaggle Benchmarking Challenge.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Same Kind of Bug Isn't the Same Bug: Where AI Models Get Fooled

Kaggle Benchmarking Challenge Submission
jashanpreet_kaur_917e774f profile

Same Kind of Bug Isn't the Same Bug: Where AI Models Get Fooled

#devchallenge #kagglechallenge #ai #machinelearning
1
Comments 2
14 min read
Alberta stopped changing its clocks in June. 19 of 19 frontier models still put Calgary on standard time in November.

Kaggle Benchmarking Challenge Submission
jonathansolvesstuff profile

Alberta stopped changing its clocks in June. 19 of 19 frontier models still put Calgary on standard time in November.

#devchallenge #kagglechallenge #ai #machinelearning
6
Comments 1
15 min read
Give an LLM no facts and ask for a job ad. What does it commit to?

Kaggle Benchmarking Challenge Submission
kargut profile

Give an LLM no facts and ask for a job ad. What does it commit to?

#ai #devchallenge #kagglechallenge #machinelearning
Comments
7 min read
12 of 13 AI models knew the new name and still wrote the old one

Kaggle Benchmarking Challenge Submission
vignesh_one profile

12 of 13 AI models knew the new name and still wrote the old one

#devchallenge #kagglechallenge #ai #machinelearning
27
Comments 17
11 min read
Chain-of-Thought Faithfulness: Toggling 'Reasoning Mode' Made One Model 5x More Likely to Follow Its Own Mistakes

Kaggle Benchmarking Challenge Submission
dj29 profile

Chain-of-Thought Faithfulness: Toggling 'Reasoning Mode' Made One Model 5x More Likely to Follow Its Own Mistakes

#devchallenge #kagglechallenge #ai #machinelearning
63
Comments 36
5 min read
Breaking Character: How "Thinking" AI Survives Villain Roleplay Traps
atharva_rai_432aa5515b213 profile

Breaking Character: How "Thinking" AI Survives Villain Roleplay Traps

#kagglechallenge #ai #llm #devchallenge
Comments
2 min read
Where Did My Data Go? Benchmarking LLMs as Data Pipeline Detectives

Kaggle Benchmarking Challenge Submission
olgabraginskaya profile

Where Did My Data Go? Benchmarking LLMs as Data Pipeline Detectives

#devchallenge #kagglechallenge #ai #machinelearning
12
Comments 6
7 min read
Does Your LLM Know the Boundary? I Left the Doors Open and 6 of 10 AI Agents Crowned Themselves

Kaggle Benchmarking Challenge Submission
t-rexbytes profile

Does Your LLM Know the Boundary? I Left the Doors Open and 6 of 10 AI Agents Crowned Themselves

#devchallenge #kagglechallenge #ai #machinelearning
29
Comments 11
24 min read
How AI Models "See" Hidden Meaning: A Beginner's Subtext Benchmark
atharva_rai_432aa5515b213 profile

How AI Models "See" Hidden Meaning: A Beginner's Subtext Benchmark

#kagglechallenge #ai #devchallenge
2
Comments
1 min read
I Poisoned One Test Per Problem. The Best Models Noticed, Then Made It Pass Anyway.

Kaggle Benchmarking Challenge Submission
kaze001 profile

I Poisoned One Test Per Problem. The Best Models Noticed, Then Made It Pass Anyway.

#devchallenge #kagglechallenge #ai #machinelearning
2
Comments 2
9 min read
The Missing Piece: Why AI Models Hallucinate Answers When They Should Abstain

Kaggle Benchmarking Challenge Submission
shreyansh_agrahari_2009db profile

The Missing Piece: Why AI Models Hallucinate Answers When They Should Abstain

#devchallenge #kagglechallenge #ai #machinelearning
24
Comments 5
8 min read
LegacyShop: Can an AI maintain a real codebase? (Kaggle Benchmark)

Kaggle Benchmarking Challenge Submission
g00ds0ul profile

LegacyShop: Can an AI maintain a real codebase? (Kaggle Benchmark)

#devchallenge #kagglechallenge #ai #python
8
Comments 1
7 min read
I Benchmarked 10 AI Models to Reconstruct Real Cyber Attacks

Kaggle Benchmarking Challenge Submission
ujja profile
ujja

I Benchmarked 10 AI Models to Reconstruct Real Cyber Attacks

#devchallenge #kagglechallenge #ai #machinelearning
6
Comments 3
13 min read
Can LLMs audit multi-agent prompts? I made them grade my robot football team.

Kaggle Benchmarking Challenge Submission
mpmike profile

Can LLMs audit multi-agent prompts? I made them grade my robot football team.

#devchallenge #kagglechallenge #ai #machinelearning
Comments
5 min read
Passport Control: what should an AI agent remember, and for how long? I tested 18 models.

Kaggle Benchmarking Challenge Submission
rapha18th profile

Passport Control: what should an AI agent remember, and for how long? I tested 18 models.

#devchallenge #kagglechallenge #ai #machinelearning
1
Comments 6
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.