Opinion

OpenAI Codex team member explains discrepancy between 6.2 Sol/Astra evaluation video and live feedback

Original title:One of the funny reasons for the difference in vibes between the influencers and the crowd today on 6.2 Sol/Astra is that we gave a few f...

AI summary

Tibo explains why the evaluation video for 6.2 Sol/Astra differs from the atmosphere of live audience feedback: some people gained access earlier, while the team made substantial changes over the past 3-4 days; the video was produced last week and most likely was not retested afterward. He says the two models show clear improvement over previous GPT generations but are still not perfect, and the team hopes to improve taste and user experience in subsequent iterations, adding that feedback is welcome.

Key Takeaways

  • Tibo explains why the evaluation video for 6.
  • 2 Sol/Astra differs from the atmosphere of live audience feedback: some people gained access…
  • the video was produced last week and most likely was not retested afterward.
  • He says the two models show clear improvement over previous GPT generations but are still not…

Quick Facts

Published
Source
X:Tibo (@thsottiaux)
Category
Opinion
Topic
OpenAI / ChatGPT
AI score
64
Read the original Read the full article at the original source
Why it matters

作者作为当事方解释 6.2 Sol/Astra 评测视频与现场反馈差异的原因,读者可以据此校准上周视频结论的时效性。

Topics

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: OpenAI Codex team member explains discrepancy between 6.2 Sol/Astra evaluation video and live feedback. November 18, 2026. https://new.nat6.net/en/news/sah26a5ofgvrxd76bgj9t77wf/

View all →