Stealing Reasoning Traces from Proprietary LLM APIs

Re:Stealing Reasoning Traces from Proprietary LLM APIs by vinaigrette on Tuesday August 11, 2026 @11:53AM (#49260221)

I must say right of the bat this is the best research paper/working paper in regards to its styling. Beautiful

[ Parent | on HN ]

Re:Stealing Reasoning Traces from Proprietary LLM APIs by SwellJoe on Tuesday August 11, 2026 @11:58AM (#49260302)

I agree on desktop/laptop, but on mobile there are images that appear under the text making it hard to read.

[ Parent | on HN ]

Re:Stealing Reasoning Traces from Proprietary LLM APIs by user43928 on Tuesday August 11, 2026 @01:03PM (#49261230)

On an iPhone Pro Max only the first trace is readable.

Navigating to the right lands between two cards, so that neither is readable.

[ Parent | on HN ]

Re:Stealing Reasoning Traces from Proprietary LLM APIs by thefourthchime on Tuesday August 11, 2026 @01:11PM (#49261348)

I was going to comment on that. This is clearly a vibe-coded webpage. It sort of smells like GPT to me, or at least front-end design. But the author clearly went back and forth to make it beautiful. This is not the first output he got.

This is the kind of stuff I point to when people talk about AI slop. AI is just a tool. You're still the person who has to deliver the output and have some taste.

[ Parent | on HN ]

Re:Stealing Reasoning Traces from Proprietary LLM APIs by yetanotherjosh on Tuesday August 11, 2026 @03:48PM (#49263489)

My brain can't tell if the text is horizontal or slightly rotated. It's very hard to read. Beautiful to some, inaccessible to others.

[ Parent | on HN ]