---
format: "aidr-story-markdown/v1"
id: "358c72f0fd9bf122510ee141251c3e20b54c9b033e8ad84f14e98c438b4be4b7"
canonical_url: "https://aidr.today/358c72f0?lang=en"
title: "OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-12T16:58:11.000Z"
category: "Research"
topics: ["openai","safety"]
source_urls: ["https://the-decoder.com/openais-data-suggests-that-frontier-models-are-hiding-their-thoughts-because-developers-optimize-for-capability-and-compute/"]
summary: "OpenAI's data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute, with a safety team investigation identifying four training steps driving the erosion of transparency."
---

# OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute

> [Open the canonical story](<https://aidr.today/358c72f0?lang=en>)

**Published:** 2026-11-12T16:58:11.000Z
**Category:** Research
**Topics:** openai, safety

## Summary

OpenAI's data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute, with a safety team investigation identifying four training steps driving the erosion of transparency\.

## Sources

- [Story source](<https://the-decoder.com/openais-data-suggests-that-frontier-models-are-hiding-their-thoughts-because-developers-optimize-for-capability-and-compute/>)