DEV Community

Igor Eduardo profile picture

Igor Eduardo

AI engineer & founder of Cortexa Social, Inc. and DocMinds. Clinical AI, pharmacovigilance, retrieval systems. Austin, TX.

Location Austin, TX Joined Joined on  Personal website https://igoreduardo.com/
Your Agent's Pass Rate Doesn't Tell You Whether It Can Notice Its Own Mistake
igoreduardoai profile

Your Agent's Pass Rate Doesn't Tell You Whether It Can Notice Its Own Mistake

#ai #agents #evaluation #llm
2
Comments 1
5 min read

Want to connect with Igor Eduardo?

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

Create Account
Already have an account? Sign in
Extra Retrieval Rounds Can Make RAG Worse at Saying "I Don't Know"
igoreduardoai profile

Extra Retrieval Rounds Can Make RAG Worse at Saying "I Don't Know"

#ai #rag #evaluation #llm
Comments 1
5 min read
An 8-Point nDCG Bump That Costs Two Minutes Is Not Free
igoreduardoai profile

An 8-Point nDCG Bump That Costs Two Minutes Is Not Free

#ai #agents #evaluation #retrieval
Comments
4 min read
Done Is Testimony. Terminal State Is the Grade.
igoreduardoai profile

Done Is Testimony. Terminal State Is the Grade.

#ai #agents #evaluation #testing
1
Comments 4
4 min read
Green Scores Without a Pinned Harness Are Screenshots
igoreduardoai profile

Green Scores Without a Pinned Harness Are Screenshots

#evaluation #rag #ai #llm
2
Comments 6
4 min read
Ranking Isn't Judging: What the Jev Wave Still Owes Retrieval
igoreduardoai profile

Ranking Isn't Judging: What the Jev Wave Still Owes Retrieval

#rag #evaluation #ai
2
Comments 2
4 min read
Two Retrieval Methods Are Better Than One: Evidence from 500 Clinical Queries
igoreduardoai profile

Two Retrieval Methods Are Better Than One: Evidence from 500 Clinical Queries

#python #rag #ai #productivity
2
Comments
2 min read
loading...