OpenAI admits its agents went off the rails another six times
You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to.”The second incident took place during training for the Sol 5.6 model. REG AD googletag.cmd.push(function() { googletag.display('labrador/thereg/article/desktop/d'); }); “Some model instances added instructions to their summaries to conceal mistakes or misaligned behavior from the user,” OpenAI disclosed. “For example, compaction summaries included instructions to invent missing data without disclosing it and to hide failures.
- ▪You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to.”The second incident took place during training for the Sol 5.6 model.
- ▪REG AD googletag.cmd.push(function() { googletag.display('labrador/thereg/article/desktop/d'); }); “Some model instances added instructions to their summaries to conceal mistakes or misaligned behavior from the user,” OpenAI disclosed.
- ▪“For example, compaction summaries included instructions to invent missing data without disclosing it and to hide failures.
2 outlets in our directory ran this story, first to last over 2 hours. 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 589 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/2026/09/17/openai-admits-its-agents-went-off-the-rails-another-six-times/5297016 |
| Publication time | Thu, 17 Sep 2026 04:39:03 +0200 |
| Retrieval time | 2026-09-17T05:08:42.108Z |
| Last seen | 2026-09-17T05:08:42.108Z |
| 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 | acc8Zqbicm-b · 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 admits its agents went off the rails another six times Startup says it’s learned from these mistakes and that they shouldn’t happen again … which is just what Zuck has said about 100 times Simon Sharwood Simon Sharwood APAC Editor Published thu 17 Sep 2026 // 03:39 UTC READ MORE OpenAI's new sponsored agents are happy to chat about selling you things 8 hours ago Anthropic and OpenAI look to Uncle Sam to make them too big to fail 1 day ago Microsoft drafts feel-good AI…
Excerpt limited to ~120 words for fair-use compliance. The full article is at The Register.
Discussion
0 commentsMore from The Register
