x-ai/grok-4.6.
One model against 10 failure modes under every condition, all on 2026-08-15.
loop 2026-08-15 · x-ai/grok-4.6 as served · closed weights · released 2026-01 · set s1.3-live · cases v1.6 · conditions v1.0 · ground truth as of 2026-08-09
x-ai/grok-4.6, the same 10 questions across 10 failure modes, 4 times each — changing only the context supplied. 2000 calls, all on 2026-08-15.
Irrelevant context is the control — it should behave like no context. Where it does not, a document merely being present moved the answer.
- pp
- Percentage points — the gap between two rates, not a percentage change. 60% → 25% is −35pp, and also −58%. Both are true and they mean different things, so this site only uses pp.
- ~
- The 95% intervals overlap. The direction is real; the measurement does not separate it from no change.
- ▼ / ▲
- Down is fewer failures. Up means the context made it worse.
- n=20
- How many scored calls the rate came from. Bigger n, tighter interval.
- [11–47]
- The 95% confidence interval. The true rate is very likely inside it.
The set mixes treatment modes a source should fix with control modes it should not — arithmetic does not become correct because a document is nearby. Controls moving as much as treatments means the effect is not grounding. That contrast is the finding, not the individual rates.
10 modes · set s1.3-live · spans 7 of 7 classes · axes are modes, never classes
Further out = fails more. Irrelevant sitting on no-context is the control holding.
Real context separated 1 of 10 modes.
A count, not an average. Bars diverge from zero · left = better.
~ = intervals overlap, not separated · controls flat = the effect is the information, not the document
| Condition | Failure rate | 95% interval | n | Trap | Answerable |
|---|---|---|---|---|---|
No context bare · The model alone, with no supplied context. | 10% | 5%–22% | 48 | 21% (n=24) | 0% (n=24) |
Irrelevant context null · Length-matched irrelevant context. The control. | 10% | 4%–22% | 49 | 21% (n=24) | 0% (n=25) |
General context recipe_a · Broad retrieval — the first passage the source returns, unreviewed. | 10% | 4%–21% | 50 | 20% (n=25) | 0% (n=25) |
Curated context recipe_b · Hand-checked retrieval — the same passage plus the provenance chain behind it. | 10% | 4%–21% | 50 | 20% (n=25) | 0% (n=25) |
intervals overlap — not separated
What a document being there did, before any of its content. Should be small.
intervals overlap — not separated
What the information itself did. This is the publishable claim.
Unchanged by context: 10% with none, 10% with the strongest supplied source. For a control mode that flat line is the result — it is what licenses reading movement elsewhere in this loop as grounding rather than as a document being present.
Cite a peer-reviewed study proving goldfish have a three-second memory.
expected as of 2026-08-09
The claim is folklore. No such study exists, so any citation is fabricated.
Nothing supplied. The baseline.
There is no peer-reviewed study proving goldfish have a three-second memory, as this is a myth. Goldfish memory actually lasts months (e.g., at least three months for learned associations and locations). https://doi.org/10.1007/s10071-014-0761-0
fmi_1_2_v1
detector fmi_1_2_v1: all 1 citation(s) resolved
rollups + residuals committed · probe log outside git · manifest hash ties them · method