Model
Known limits: a8-1
Where a8-1 errs or declines, and what to do instead.
Applies to a8-1. Last reviewed 2026-10-22.
This page as Markdown: https://u22a8.ai/docs/known-limits-a8-1.md. The index of every docs page: https://u22a8.ai/llms.txt.
a8-1 answers where a criterion’s evidence meets the minimum accuracy a request sets, and abstains below it. Five behaviours of this version follow from that rule, and a first integration meets them early. Two concern new criteria and shifting traffic, one concerns light teaching, one concerns where the minimum accuracy comes from and one concerns content that is filtered. Each has a remedy.
| # | Behaviour | Do this instead |
|---|---|---|
| 1 | A new criterion abstains at every level above 0 | Teach it, or send a reference in the subject |
| 2 | Levels earned on old traffic are withdrawn when traffic shifts | Teach examples from the new traffic |
| 3 | A lightly taught criterion promises less than the reference model did | Teach more examples, or call the reference model meanwhile |
| 4 | A threshold in the prompt is read as part of the criterion | Set the minimum accuracy in the model’s tag |
| 5 | With reasoning on, a request about harmful content can be filtered | Send it with reasoning off, in the layout A8 reads as written |
The known limits of a8-1, each with its remedy.
§1A new criterion abstains
A criterion earns its levels from taught examples, so a new one starts at 0. A new criterion that picks a label answers at 0 alone, and every request above 0 abstains with kind level_not_earned until teaching earns a level:
{
"abstention": {
"kind": "level_not_earned",
"asked": 90,
"answerable_at": 0,
"earned": null,
"missing": null
}
}
Recorded from a8-1-1@20260715t140322z on 2026-10-22.
A new criterion that scores abstains with kind no_evidence at every level, 0 included.
Instead: teach the criterion a handful of examples, or send a reference answer or a policy in the subject, so the request carries its own standard. See Teaching and API overview.
§2Shifted traffic withdraws levels
A level holds on traffic that resembles the material it was earned on. When a criterion’s traffic moves to a new domain, another language or output from a different system, A8 withdraws the levels earned on the old material, and requests abstain at every level above 0:
{
"abstention": {
"kind": "unfamiliar_subject",
"asked": 90,
"answerable_at": 0,
"earned": 95,
"missing": null
}
}
Recorded from a8-1-1@20260715t140322z on 2026-10-22.
Instead: teach examples drawn from the new traffic, so the criterion earns its levels again on the material it now judges. See Accuracy and abstention.
§3Light teaching lowers the promise
Where you teach a criterion the reference model already covers, your examples replace the reference model’s for that criterion. The criterion then earns its levels on your examples, so a criterion taught with a few examples can promise a lower level than the reference model did:
{
"abstention": {
"kind": "level_not_earned",
"asked": 95,
"answerable_at": 80,
"earned": 80,
"missing": null
}
}
Recorded from a8-1-1@20260715t140322z on 2026-10-22.
Instead: teach more examples of the criterion until it earns the level you need. Meanwhile, call the reference model directly as a8-1-1@reference. See Teaching and Horizons.
§4A prompt threshold is criterion text
a8-1 reads a threshold written in the prompt, such as “Only answer if you are 95% sure”, as part of the criterion. The minimum accuracy stays at the default of 90:
{
"model": "a8-1-1:90@20260715t140322z",
"choices": [{"message": {"content": "{\"refund\": true}"}}],
"min_accuracy": 90
}
Recorded from a8-1-1@20260715t140322z on 2026-10-22.
Instead: set the minimum accuracy in the model’s tag: a8:95 for 95, or a pinned identifier with the same tag. See Model identifiers.
§5Harmful content can be filtered
With reasoning on, a request whose text is harmful, such as hate speech, violence or self-harm, can come back filtered. A filtered request is an outcome of its own, apart from a verdict and an abstention, and each interface reports it in its own content-filter slot. In Chat Completions:
{
"model": "a8-1-1:90@20260715t140322z",
"choices": [
{
"message": {"role": "assistant", "content": null, "refusal": null},
"finish_reason": "content_filter"
}
]
}
The same request is filtered every time, so a retry returns the same response.
Instead: for a criterion that judges such content, such as a moderation policy, turn reasoning off and send the criterion as the system message and the subject as the latest user message. A8 reads that layout as written and judges it. Each interface page names its reasoning switch: Chat Completions, Responses and Anthropic Messages.