DEV Community

Rickesh T N profile picture

Rickesh T N

CV and robotics engineer. 15 years in production software, 9 taking deep learning from research to deployed systems. I write about evaluation and training data, and the ways both quietly fail.

Education

M.Sc. Digital Media Technology, Nanyang Technological University

Pronouns

He/Him

Work

Senior Computer Vision Engineer, Applied Research at KARL STORZ

My inference server decided my second GPU no longer exists. Here is how I got it back without upgrading a driver.

My inference server decided my second GPU no longer exists. Here is how I got it back without upgrading a driver.

Comments
3 min read

Want to connect with Rickesh T N?

Create an account to connect with Rickesh T N. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
A generic fine-tuning playbook, written after doing it wrong several times

A generic fine-tuning playbook, written after doing it wrong several times

1
Comments 1
6 min read
A 4B model on a 6GB laptop beat Claude Opus on our 440K-token corpus. The fix was giving the model less to do.

A 4B model on a 6GB laptop beat Claude Opus on our 440K-token corpus. The fix was giving the model less to do.

1
Comments 1
4 min read
99% token accuracy, zero learning. Field notes from fine-tuning vision models with RL.

99% token accuracy, zero learning. Field notes from fine-tuning vision models with RL.

1
Comments 3
4 min read
Your multi-agent system isn't hitting prompt cache. Your system prompt is the reason.

Your multi-agent system isn't hitting prompt cache. Your system prompt is the reason.

4
Comments 9
6 min read
Can a Cheap Model Beat a Frontier Model? Rebuilding Recursive Language Models with Codex

Can a Cheap Model Beat a Frontier Model? Rebuilding Recursive Language Models with Codex

2
Comments
6 min read
We made our world model smaller and it got better. Then "efficient" attention made nothing faster.

We made our world model smaller and it got better. Then "efficient" attention made nothing faster.

6
Comments 2
5 min read
Three Ways Your Training Data Lies to You (And None of Them Throw an Error)

Three Ways Your Training Data Lies to You (And None of Them Throw an Error)

6
Comments 6
5 min read
Your reasoning model isn't dumb. Your parser is throwing away its best answers.

Your reasoning model isn't dumb. Your parser is throwing away its best answers.

1
Comments 4
4 min read
loading...