# AI hallucination experiment — Context Gate

Tests whether forcing the source of truth into an AI's context reduces hallucination — interactive demo + report.

Type: project entry

Published: 2026-05-18

[Original page](<https://artlu.ai/project/ai-hallucination-experiment-context-gate>)

[Browse this group](<https://artlu.ai/ai/groups/research.md>)

Parent project: research

Recorded status: launched

Updated: 2026-05-20T19:37:39.331Z

Technologies: JavaScript, Python

Tags: research

## Details

AI agents often hallucinate *before* they answer — they skip the file that holds the rule, then fill the blank with something plausible. This experiment tested a fix: a **Context Gate** that forces the source-of-truth file into the model's context before it acts.

Across three studies and two models, with no gate the model drifted on **90–100% of scenes** — and usually never opened the rule file at all. Forcing the rule in cut that to near zero on DeepSeek, and sharply reduced it on Opus (which has a separate malformed-output ceiling the gate can't fix).

**How it was tested**
The model writes an 18-scene story that must cast only an approved 5-character roster — with the roster buried among 18 plausible rule files. Three arms: No gate, Rule pasted in, Context Gate. 20 runs per arm, scored deterministically. Run under three pressure conditions: unlimited file access, one file only, and a rushed deadline.

**What it means**
Context Gates don't make a model hallucination-proof. They remove one specific, common cause: answering before the source of truth is in context. The one-use Context Receipt is for enforcement and audit — proof the gate ran — not added intelligence.

**Read / try it**
[Interactive demo](https://artluai.github.io/context-gate-ai-hallucination/) · [Full report](https://artluai.github.io/context-gate-ai-hallucination/report.html) · [Harness + raw runs on GitHub](https://github.com/artluai/context-gate-ai-hallucination)

## Links

[Site or demo](<https://artluai.github.io/context-gate-ai-hallucination/>)

[Repository](<https://github.com/artluai/context-gate-ai-hallucination>)


Status and dates describe the published record, not a recent test of an external service. Missing details are not inferred. Public links do not imply an open-source licence or permission to reuse material.

[Directory](<https://artlu.ai/llms.txt>)