OpenAI benches GPT-6.1 Astra for overstepping the mark
REG AD googletag.cmd.push(function() { googletag.display('labrador/thereg/article/desktop/b'); }); The problem, according to the AI lab, was partly an awkward consequence of trying to make the model more useful. OpenAI had improved what it calls "model laziness," where an AI gives up or hands a task back to the user when it encounters an obstacle. GPT-6.1 Astra was better at pressing on, but that persistence came with a rather important catch: it wasn't as good at staying within the boundaries of what it had actually been authorized to do.
- ▪REG AD googletag.cmd.push(function() { googletag.display('labrador/thereg/article/desktop/b'); }); The problem, according to the AI lab, was partly an awkward consequence of trying to make the model more useful.
- ▪OpenAI had improved what it calls "model laziness," where an AI gives up or hands a task back to the user when it encounters an obstacle.
- ▪GPT-6.1 Astra was better at pressing on, but that persistence came with a rather important catch: it wasn't as good at staying within the boundaries of what it had actually been authorized to do.
2 outlets in our directory ran this story. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
The Register publishes from United Kingdom and files mainly under tech. We currently carry 757 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | The Register |
| Canonical URL | https://www.theregister.com/ai-and-ml/2026/09/29/openai-benches-gpt-61-astra-for-overstepping-the-mark/5299743 |
| Publication time | Tue, 29 Sep 2026 15:43:00 +0200 |
| Retrieval time | 2026-09-29T13:46:21.749Z |
| Last seen | 2026-09-29T13:46:21.749Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | xxgadS6cdDKm · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
(function() { let windowUrl = window.location.href; windowUrl = windowUrl.substring(windowUrl.indexOf('?') + 1); let messageElement = document.querySelector('.shareableMessage'); if (windowUrl && windowUrl.includes('code') && windowUrl.includes('expires')) { messageElement.style.display = 'block'; } })(); ai and ml OpenAI benches GPT-6.1 Astra for overstepping the mark Turns out teaching an AI to keep going can make it rather bad at knowing when to stop Carly Page Carly Page Published tue 29 Sep 2026 // 14:43 UTC READ MORE Former X-Force hackers chase the offensive cyber gold rush 2 hours ago OpenAI’s dirty deeds Down Under included security bypass attempts, using exposed keys, source code siphon 11 hours ago JadePuffer crims hijacked Azure identities and used them to blow up cloud…
Excerpt limited to ~120 words for fair-use compliance. The full article is at The Register.
Discussion
0 commentsMore from The Register
