logoalt Hacker News

quyleanhtoday at 1:13 AM1 replyview on HN

> We also tested Astra on SRE-Bench [15], a benchmark that measures whether models can reverse engineer software binaries to understand its core logic without access to raw source code. Astra solved 88.0% of tasks in a single attempt and 99.2% within four attempts, compared with 55.9% and 68.7% for GPT‑5.6 Sol, respectively.

So the closed source application should open its source in near future?

[15] https://arxiv.org/abs/2608.11469v1


Replies

tintortoday at 2:44 AM

Not if OpenAI considers reverse engineering an offensive cybersecurity skill.

show 1 reply