Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Private Safety Processing lets OpenAI review related API requests for safety without retaining your prompts or responses. Records stay in your environment, where an automated safety agent reviews them without OpenAI personnel being able to access your content.

69,173 görüntüleme • 12 gün önce •via X (Twitter)

28 Yorum

OpenAI Developers profil fotoğrafı
OpenAI Developers12 gün önce

See how it works and connect your cloud storage:

rohit profil fotoğrafı
rohit12 gün önce

Ayyy I recognised a goat here! @codestantine

Zapidroid profil fotoğrafı
Zapidroid12 gün önce

shut up till you release a model sincerely ~Everyone 💖

Godan Lee profil fotoğrafı
Godan Lee12 gün önce

支持你们,希望你们的产品越来越好。💪

Phavorism profil fotoğrafı
Phavorism12 gün önce

The key word is "related". One request on its own rarely looks like misuse, a pattern across many calls does. So they review requests together, and the trade is that no OpenAI staff read them, an agent does, and the records stay in your environment Most of what I send to models is storyboards and render scripts for Claude Code films, so this matters less to me. For teams putting contracts or medical records through an API it's probably the first question, before anything about model quality

K-AI profil fotoğrafı
K-AI12 gün önce

靠

susuai profil fotoğrafı
susuai12 gün önce

划重点:ZDR+PSP 把抽检的 prompt/response 加密写进你控的存储(S3/Azure/GCS/OCI),OpenAI 只留索引元数据+存储引用。审核在硬件证明、禁人工访问的 Runtime 跑,明文只出有界安全信号,TTL 30 天。想问:一开是整个 project 全量走 PSP,还是可按模型/端点豁免?

Joby Oommen profil fotoğrafı
Joby Oommen12 gün önce

Shouldn’t this just be a built in standard? The beauty of Astra 6 is no need for us non-software engineers to have to figure things out or use Cursor etc. The Ai model should handle all complexities. Human ideas are our “IP”, rare and valuable, should be protected from the start. @sama @gdb @thsottiaux @OpenAI

Leo Choi profil fotoğrafı
Leo Choi12 gün önce

openai says a bot reads your requests so no human has to. best coworker ever, zero gossip

Mohit profil fotoğrafı
Mohit12 gün önce

AI safety without sacrificing data privacy. That's an interesting direction. The future of AI needs both security and user trust.

Mohit | Software Engineer profil fotoğrafı
Mohit | Software Engineer12 gün önce

so my agent gets a hall monitor that lives on my infra. whose tokens does it burn

Jeff Bruchado profil fotoğrafı
Jeff Bruchado12 gün önce

if nobody at openai can see the content, appealing a false positive from that safety agent gets awkward fast

xia profil fotoğrafı
xia12 gün önce

我们想要的是一个新的模型,不是这个东西

Ghost profil fotoğrafı
Ghost12 gün önce

this matters a lot for anyone building on health or finance data. real q tho, do devs get told why a request got flagged or is it just vibes

Lourens profil fotoğrafı
Lourens12 gün önce

and when the agent flags it, who looks?

lewington profil fotoğrafı
lewington12 gün önce

even the moderation logs are going private…..

Aleksandar Janca profil fotoğrafı
Aleksandar Janca12 gün önce

the prompts still leave the building to get answered though, this settles the retention question, not the one most of my clients actually ask

Ram Pathath profil fotoğrafı
Ram Pathath12 gün önce

I never liked sending prompts out just for a safety check

nick profil fotoğrafı
nick12 gün önce

haha finally — safety review without keeping the data is the bit everyone skips 😅

Sachin profil fotoğrafı
Sachin12 gün önce

Come on dude stop with these nothingburger posts and release a fucking model soon

inhza profil fotoğrafı
inhza12 gün önce

I thought it was.....

JonsTech profil fotoğrafı
JonsTech12 gün önce

Records staying in your own environment is a big deal tbh. That's the bit that's stopped a lot of companies going all in on the API

ShadowAguy profil fotoğrafı
ShadowAguy12 gün önce

my local agents finally have an OpenAI safety agent to argue with.

THUNDER⚡ profil fotoğrafı
THUNDER⚡12 gün önce

double encryption keeps content locked to customer keys

CRusty profil fotoğrafı
CRusty12 gün önce

just put the model in the api bro

JL profil fotoğrafı
JL12 gün önce

新模型什么时候来?

Sgkkg Kdjgm profil fotoğrafı
Sgkkg Kdjgm12 gün önce

The diagram ends at "limited safety signals" and doesn't say what's in them. If a signal can carry a summary of the flagged prompt, the content still leaves your cloud, just shorter.

Russell | The Gaming Strategist profil fotoğrafı
Russell | The Gaming Strategist12 gün önce

So an AI agent checks the AI agents. Who reviews the safety agent though? What a time to be alive lol

Benzer Videolar