SafetyPublished All news from that day
OpenAI reorganises its Model Spec around five values and retires much of its detailed style guidance.
OpenAI says the Spec describes behavior it is working toward and its models do not yet fully reflect it.
Check our sources · 6 facts from 1 sourceOpenAI reorganised its Model Spec, the public description of how it wants its models to behave, around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. The change is described in an OpenAI post of 29 October 2026.
The update adds guidance on context, oversight and agency, adjusts some behavioural defaults, and retires most of the detailed style guidance. The Spec now refers to the model as GPT rather than the assistant. OpenAI says its models do not yet fully reflect the Spec, and that it is exploring new training methods to teach the values, with results promised in future updates.
Your reaction
We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.
We count reactions per story and day, never who reacted. They help choose what goes in the monthly issue.
Check our sources
Every sentence above is checked against this source.
1 An updated Model Spec for more capable and beneficial AI
Open the source archived copy-
OpenAI's post An updated Model Spec for more capable and beneficial AI is dated 29 October 2026.
citeOctober 29, 2026 Safety An updated Model Spec for more capable and beneficial AI
-
OpenAI says the update reorganizes the Model Spec's guidance around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care.
citeThe update reorganizes its guidance around five underlying values: faithfulness to human intent , harm minimization , honesty and transparency , human agency , and care .
-
OpenAI says the revision adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.
citethe revision adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.
-
OpenAI says it now refers to the model as GPT rather than the assistant in the Spec.
citewe now refer to the model as “GPT” rather than “the assistant” in the Spec.
-
OpenAI says the Model Spec describes the behavior it is working toward and that its models do not yet fully reflect it.
citeThe Model Spec describes the behavior we are working toward; our models do not yet fully reflect it.
-
OpenAI says it has been exploring new training methods to help its models learn these core values and follow the Spec's behavioral principles, and that it will share results in future updates.
citewe’ve been exploring new training methods to help our models learn these core values
Every sentence above is checked against this source. Each fact has its own address you can cite.
Source 1 · OpenAI · 29 Oct 2026
An updated Model Spec for more capable and beneficial AI
OpenAI's post An updated Model Spec for more capable and beneficial AI is dated 29 October 2026.
October 29, 2026 Safety An updated Model Spec for more capable and beneficial AI
OpenAI says the update reorganizes the Model Spec's guidance around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care.
The update reorganizes its guidance around five underlying values: faithfulness to human intent , harm minimization , honesty and transparency , human agency , and care .
OpenAI says the revision adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.
the revision adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.
Show all 6 factsShow fewer facts
OpenAI says it now refers to the model as GPT rather than the assistant in the Spec.
we now refer to the model as “GPT” rather than “the assistant” in the Spec.
OpenAI says the Model Spec describes the behavior it is working toward and that its models do not yet fully reflect it.
The Model Spec describes the behavior we are working toward; our models do not yet fully reflect it.
OpenAI says it has been exploring new training methods to help its models learn these core values and follow the Spec's behavioral principles, and that it will share results in future updates.
we’ve been exploring new training methods to help our models learn these core values
Topics
The morning email
On the mornings we publish: the three top stories and up to four short ones. Free.
We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep