[go: up one dir, main page]

DEV Community

Rudratosh Shastri profile picture

Rudratosh Shastri

Backend architect, 15 years deep. Still curious, still shipping. Systems • AI Agents • Security • Breaking things on purpose 🔥

Location Indore,MP Joined Joined on  Email address rudratoshs@gmail.com Personal website https://exportbankstatement.com github website

Education

Studied Computer Science at Arya Institute of IT

Pronouns

He

Work

Technical Lead & Senior Backend Architect at PharmaForceIQ

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

Kaggle Benchmarking Challenge Submission
rudratosh profile

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

#kagglechallenge #ai #machinelearning #llm
5
Comments 1
6 min read

Want to connect with Rudratosh Shastri?

Create an account to connect with Rudratosh Shastri. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
I Almost Built a Startup This Week. The Evidence Said No — In One Afternoon.
rudratosh profile

I Almost Built a Startup This Week. The Evidence Said No — In One Afternoon.

#discuss #startup #career #ai
6
Comments 10
5 min read
10 Years In, Everything I Was Proud Of As a Junior Was Wrong
rudratosh profile

10 Years In, Everything I Was Proud Of As a Junior Was Wrong

#discuss #career #backend #programming
5
Comments 1
4 min read
Your AI Agent Will Follow a Stranger's Instructions. Here's How I Actually Test For It.
rudratosh profile

Your AI Agent Will Follow a Stranger's Instructions. Here's How I Actually Test For It.

#ai #security #python #opensource
5
Comments 1
5 min read
The Hidden Bill: Where AI Agent Costs Actually Come From
rudratosh profile

The Hidden Bill: Where AI Agent Costs Actually Come From

#ai #agents #llm #cost
5
Comments 5
5 min read
I tested 10 prompt-injection detectors on 629 real AI agent attacks
rudratosh profile

I tested 10 prompt-injection detectors on 629 real AI agent attacks

#ai #security #llm #opensource
5
Comments 5
4 min read
Sanity's Knowledge Base stopped 6 of 7 poisoned pages. The 7th fooled Claude Opus 5.

Sanity Challenge Path One Submission
rudratosh profile

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

#devchallenge #sanitychallenge #sanity #ai
5
Comments 1
7 min read
AI agents can't tell who's giving the orders. So I built a tiny gate.
rudratosh profile

AI agents can't tell who's giving the orders. So I built a tiny gate.

#ai #security #python #opensource
5
Comments 3
7 min read
loading...