Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Codex starts encrypting sub-agent prompts

github.com

Post reply on HN
Print view View original

171–180 of 272 posts

Re: Codex starts encrypting sub-agent prompts

#171

Post by dmurray »

bartread wrote: post #134
dmurray wrote: post #79

Earlier quoted context omitted.

Perhaps AI providers should support this natively: the customer supplies the API key but doesn't get access to the transcripts.

I don't know how you'd enforce that unless it was something you could mandate at the level of the API call, and then the API call is rejected if the customer hasn't configured it for "no transcript". It sort of feels like an area of friction even still.

I was thinking of an API key that was scoped both to a specific customer and a specific service provider (perhaps both have to do something to provision it).

Billing goes to the customer, debug logs etc go to the service provider.

Re: Codex starts encrypting sub-agent prompts

#172

Post by ctkhn »

pornel wrote: post #165
EGreg wrote: post #151

Earlier quoted context omitted.

It seems their incentives aren’t exactly aligned with their users, including corporate users. Look at the latest statements from Alex Karp, and now Satya Nadella etc. Is this user-hostile? Encrypting stuff from the user is what RIAA used to do with DRM, worried about copyright infringement.

Nothing by Alex Karp is aligned with any users. This guy is a mercenary, and he seems to be in this job for the love of killing.

I thought tweaking was his highest calling

Re: Codex starts encrypting sub-agent prompts

#173

Post by dist-epoch »

hansihe wrote: post #117
niam wrote: post #34

This title is easy to misinterpret. If I understand correctly: Codex now encrypts sub-agent prompts and hides those prompts from the user. edit: originally was "Codex starts encrypting prompts, uses cyphertext for inference instead"

It seems likely to me this was driven by the `ultra` mode in 5.6, which fans subagents to do work. This mode was previously only available in the web UI (what was previously known as pro?) It seems possible they trained this by doing full RL rollouts of agents interacting with each other. They likely view these prompts somewhat the same as raw reasoning traces, they don't want people to train directly on them. I am u…

> latent space representation of the conversation

and how would you load that back into the model? they are token-in, token-out, plus the KV-cache which is derived from token-in

Re: Codex starts encrypting sub-agent prompts

#174

Post by LeBit »

b40d-48b2-979e wrote: post #163
fidotron wrote: post #162

Earlier quoted context omitted.

[flagged]

training people to believe that them having impossible to inspect encrypted channels from your machines to theirs is a best practice Oh yeah, I much preferred when my government and whoever controls the infrastructure could snoop on my traffic instead!

How did they do that?

Re: Codex starts encrypting sub-agent prompts

#175

Post by airstrike »

b40d-48b2-979e wrote: post #163
fidotron wrote: post #162

Earlier quoted context omitted.

[flagged]

training people to believe that them having impossible to inspect encrypted channels from your machines to theirs is a best practice Oh yeah, I much preferred when my government and whoever controls the infrastructure could snoop on my traffic instead!

idk about you but I'd rather not be murdered regardless of who the perpetrator might be

Re: Codex starts encrypting sub-agent prompts

#176

Post by ATMLOTTOBEER »

bob1029 wrote: post #93

I've been sticking with the chat completion endpoint because of this same behavior. OAI has been subtly pushing users away from chat completion and toward the endpoints that are possible to obfuscate (responses API). With chat completion, the reasoning process is entirely under your control. You can build a reasoning agent that uses custom MCTS techniques with GPT5.6 models today if you are willing to get your hands…

Can you not abuse “mcts” as a buzzword like this

The thing you’re gesturing at isn’t mcts in any real sense

Re: Codex starts encrypting sub-agent prompts

#177

Post by skywhopper »

b40d-48b2-979e wrote: post #163
fidotron wrote: post #162

Earlier quoted context omitted.

[flagged]

training people to believe that them having impossible to inspect encrypted channels from your machines to theirs is a best practice Oh yeah, I much preferred when my government and whoever controls the infrastructure could snoop on my traffic instead!

You’ve been misled about how encryption works apparently.

Re: Codex starts encrypting sub-agent prompts

#179

Post by znnajdla »

bigbaguette wrote: post #62
flexagoon wrote: post #50

Earlier quoted context omitted.

> but also store data and sell to whoever is training I see this as an argument against using them/Chinese models all the time, but I don't get it. I totally understand wanting to keep your data private if you're using an LLM for personal chats. But coding? I'm not working for the military, I'd gladly donate my codebase to Chinese labs if that means they can keep releasing 6-months-behind level models for 100x cheape…

When you work on proprietary code with a lot of trade secrets contained in it, on a codebase that did cost millions of dollars of man-hours to build and that holds the company's IP, you tend to be very careful where you're sending that to.

If you think your codebase is your competitive advantage or trade secret, you're in for bad time. AI coding has made code cheap it's the least valuable part of the value add for most companies. Almost any software company can easily be replicated with a few AI prompts. The real proprietary value is in the marketing distribution partnerships and data, not code.

Re: Codex starts encrypting sub-agent prompts

#180

Post by b40d-48b2-979e »

LeBit wrote: post #174
b40d-48b2-979e wrote: post #163

Earlier quoted context omitted.

training people to believe that them having impossible to inspect encrypted channels from your machines to theirs is a best practice Oh yeah, I much preferred when my government and whoever controls the infrastructure could snoop on my traffic instead!

How did they do that?

Does the word "plaintext" mean anything to you?
Post reply on HN