Agent-to-Agent Pair Programming

Re:Agent-to-Agent Pair Programming by 3yr-i-frew-up on Friday March 27, 2026 @09:31AM (#47542445)

Back in 2024 I read a study saying: "Ask 4 LLMs the same question, if they all give you the same answer there is some 95-99% chance its correct"

Soooo... Its not just greed. There is something there.

[ Parent | on HN ]

Re:Agent-to-Agent Pair Programming by axldelafosse on Friday March 27, 2026 @10:58AM (#47543420)

Yes exactly. I’m talking about this in the article. I found out that when Claude and Codex both review the same PR and both find the same issue, our team fixes it 100% of the time.

[ Parent | on HN ]

Re:Agent-to-Agent Pair Programming by zombot on Friday March 27, 2026 @12:36PM (#47544934)

What's the point of pair programming then if they both have the same opinions?

[ Parent | on HN ]

Re:Agent-to-Agent Pair Programming by axldelafosse on Friday March 27, 2026 @01:38PM (#47545805)

They don't. And you would be surprised how a good model actually pushes back on some comments.

The point was: when they do agree, it is a very strong signal.

[ Parent | on HN ]

Re:Agent-to-Agent Pair Programming by pixl97 on Friday March 27, 2026 @12:54PM (#47545205)

There are a number of different models out there.

[ Parent | on HN ]