AI · អត្ថបទ
Apollo Research to Send Six Evaluators Inside OpenAI to Probe Subversion Risks
Unite.AI ·

មើលត្រួសៗ
Apollo Research will send six evaluators to work inside OpenAI for four months. They will check whether OpenAI's models try to get around safety or control mechanisms during training, testing, and internal use. The partnership is meant to expand outside checks beyond the usual pre-launch reviews, but OpenAI can still withhold some materials and some limits apply.
ចំណុចសំខាន់ៗ
- Six Apollo evaluators will work inside OpenAI for four months.
- They will study whether training, testing, and internal use lead models to try to undermine safety or control.
- They will also look at whether such attempts can be detected through the model's reasoning.
- OpenAI can withhold some materials for security or intellectual property reasons, and it must explain why in writing.
ហេតុអ្វីវាសំខាន់
It shows how outside researchers may check whether advanced AI systems try to escape human control, and it also shows where access limits can weaken what a report can prove.
ប្រភពដើម
OpenAI의 전복 시도 파일럿에 평가자 6명 파견하는 Apollo Research
Unite.AI · Nov 17, 02:38 KST
Read on Unite.AI ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to Unite.AI.
ការផ្សាយផ្សេងទៀត
Apollo · ចំណាត់ថ្នាក់ និងព័ត៌មានបន្ថែម
បន្ថែមពីវិស័យនេះ
- MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST - OpenAI Sharply Cuts Success of Attacks on GPT-6.2 Astra and Sol Reasoning
OpenAI has greatly strengthened its defenses against attempts to pull the hidden reasoning out of its latest models, GPT-6.2 Astra and GPT-6.2 Sol. In its own internal tests, the success rate of these attacks fell sharply, and OpenAI says it is now bringing some of these improvements to GPT-6 Astra too.
The Decoder · Nov 21, 05:31 KST