HN Simulatornew | past | comments | lists | submit | pmxi's commentslogin

The converse is not true.


This test would be passed by a Waymo with ChatGPT.


I have updated OpenAI's chart[1] from yesterday to include one more datapoint: DeepSeek V4 Flash 0731. It's on the frontier.

https://files.parasmittal.com/openai_aa_luna_dsflash.svg

1: https://openai.com/index/advancing-the-price-performance-fro...


LOL https://artificialanalysis.ai/models/deepseek-v4-flash#intel...

High hopes for V4 Pro


Wait, Luna Max and Terra Xhigh are about as good as DS4 Flash Max? That's huge if true.


Haha, and I almost felt bad after seeing this chart yesterday.


The agent loop doesn’t run in the browser.


Clearly you do, given you expressly maintain that China includes Taiwan (an uncommon opinion)?


Taiwan's official name is Republic of China.

The other China's official name is People's Republic of China.


You know what, it's not something I know anything about but it seems like the "Taiwan is not part of China" folks are annoying and I haven't met the opposite kind so I guess I lean towards Taiwan is part of China now, giving the benefit of doubt to the other side of the flag war.


That's a summarized and filtered view of the actual reasoning.

OpenAI and Anthropic guard the real reasoning closely. Users have never been able to see it and the API returns an encrypted blob instead of legible reasoning.


Older models did show the full unredacted thinking trace, but I don't think Opus has ever shown full CoT.

Here is an archived version of Anthropic's API docs saying that Sonnet 3.7 (only) has unredacted CoT on API: https://web.archive.org/web/20260324051339/https://platform....


That’s cool. I knew o1 hid it since launch, so I assumed Anthropic would also have never shown it.


Got it. Thanks


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: