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.
Promise Is Not Payment: Verification Errors That Amount Accuracy Misses

Kaggle Benchmarking Challenge Submission
soccer_skillsfreestyle_5 profile

Promise Is Not Payment: Verification Errors That Amount Accuracy Misses

#devchallenge #kagglechallenge #machinelearning #ai
Comments 2
6 min read
The Flattery Tax: I pressure-tested 29 LLMs with confident wrong users — the frontier held, the small ones folded

Kaggle Benchmarking Challenge Submission
suraj_srivastav profile

The Flattery Tax: I pressure-tested 29 LLMs with confident wrong users — the frontier held, the small ones folded

#devchallenge #kagglechallenge #ai #machinelearning
Comments 1
6 min read
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
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
58
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
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
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
8 LLMs, 480 Questions, 1 Kaggle Benchmark: Who Can Explain a Traffic Drop?

Kaggle Benchmarking Challenge Submission
nishikantaray profile

8 LLMs, 480 Questions, 1 Kaggle Benchmark: Who Can Explain a Traffic Drop?

#devchallenge #kagglechallenge #ai #machinelearning
9
Comments 13
11 min read
Does your model know when it doesn't know? A benchmark for the ESCALATE answer

Kaggle Benchmarking Challenge Submission
sean_campbell_840bd62bf7e profile

Does your model know when it doesn't know? A benchmark for the ESCALATE answer

#devchallenge #kagglechallenge #ai #machinelearning
1
Comments 4
2 min read
Three Engines, One Informed Choice: Benchmarking Orbit

Kaggle Benchmarking Challenge Submission
jsb-securedme profile

Three Engines, One Informed Choice: Benchmarking Orbit

#devchallenge #kagglechallenge #ai #machinelearning
1
Comments 9
8 min read
The Plausible PR: I Gave 4 LLMs 10 Sneaky Refactors, and They All Missed the Same Bug

Kaggle Benchmarking Challenge Submission
respect17 profile

The Plausible PR: I Gave 4 LLMs 10 Sneaky Refactors, and They All Missed the Same Bug

#devchallenge #kagglechallenge #ai #machinelearning
2
Comments 2
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.