Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

I built an 11-LLM consensus engine to detect AI hallucination

Details

External ID
48596771
Source
HN
Company
—
Product
I built an 11-LLM consensus engine to detect AI hallucination
Website domain
github.com
Launched
June 19, 2026
Cohort
—
Upvotes
6
Upvotes percentile
0.31420765027322406
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Enrichment

Theme
Vertical
Horizontal
Function
Observability & eval
Audience
Developer
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
llm hallucination detection
Manually corrected
False

Could you build this?

Yes This is an LLM wrapper that fans out a prompt across 11 different model APIs in parallel and compares or aggregates their answers using simple voting or consensus logic.

Discussion

5 comments analyzed.

Competitors mentioned: OpenRouter API, Codex

Concerns raised: How were the 11 LLMs selected (benchmarks vs arbitrary), API key setup and cost responsibility unclear, Tool hallucination testing not mentioned

Feature requests: Scale to more than 11 LLMs, Test for tool hallucination in addition to information hallucination

Competitors

Other products that read as similar to this one — 1622 launches clear the similarity bar, closest 8 shown.

Attention rank: #993 of 1623 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 233 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a observability & eval tool for Media & entertainment yet.