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

101–110 of 272 posts

Re: Codex starts encrypting sub-agent prompts

#101

Post by agumonkey »

bartread wrote: post #74
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"

I imagine this will be because a decent chunk of the IP in Codex is probably within its prompts, how they're built, and how they're sequenced and orchestrated, rather than in the codebase per se. We had this discussion a few months ago where we talked about allowing people to choose an AI provider and provide their API key, thinking about enterprises with "preferred" (read: mandated) AI suppliers. We also wanted to o…

I'm unable to understand how much value can be in low-definability non deterministic prompts. It feels like the kept the right divinity spell into a chest.

Re: Codex starts encrypting sub-agent prompts

#103

Post by jstummbillig »

embedding-shape wrote: post #70
jstummbillig wrote: post #64

What's the idea here? Why does this seem important to OpenAI?

Seems fairly obvious what the point from OpenAI's side is (protect what they see as the moat, that a model is "good at spawning sub-agents"), but what's really strange to me is that the team somehow didn't manage to push back on this, it's so clearly disadvantageous to developers who are trying to rely on Codex for real work. For this we need introspection into what exactly is going on, hiding the prompts is just so…

> protect what they see as the moat, that a model is "good at spawning sub-agents"

Yes, that is the obvious answer. I was looking for an explanation as to why and why now. Codex is open source after all. They used to not do it. Agent prompts more generally are also not encrypted, and continue to be.

This particular change just looks unintuitive to me.

Re: Codex starts encrypting sub-agent prompts

#104

Post by hnlmorg »

agumonkey wrote: post #101
bartread wrote: post #74

Earlier quoted context omitted.

I imagine this will be because a decent chunk of the IP in Codex is probably within its prompts, how they're built, and how they're sequenced and orchestrated, rather than in the codebase per se. We had this discussion a few months ago where we talked about allowing people to choose an AI provider and provide their API key, thinking about enterprises with "preferred" (read: mandated) AI suppliers. We also wanted to o…

I'm unable to understand how much value can be in low-definability non deterministic prompts. It feels like the kept the right divinity spell into a chest.

I don’t disagree with your divinity spell comparison but unfortunately there is a lot of value in the prompts because these spells are the “programming languages” of LLMs.

Re: Codex starts encrypting sub-agent prompts

#105

Post by HarHarVeryFunny »

There was a recent report on twitter of a GPT 5.6 sub-agent accidentally deleting the user's home directory.

I wonder if there was any safeguard failure due to loss of visibility into what the sub-agent was trying to do?

https://x.com/mattshumer_/status/2076794038456385546?s=20

Re: Codex starts encrypting sub-agent prompts

#106

Post by imhoguy »

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"

Yeah I thought "wow, some homomorphic encryption* stuff", but then "nah, usual greed".

* https://en.wikipedia.org/wiki/Homomorphic_encryption

Re: Codex starts encrypting sub-agent prompts

#107

Post by embedding-shape »

imhoguy wrote: post #106
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"

Yeah I thought "wow, some homomorphic encryption* stuff", but then "nah, usual greed". * https://en.wikipedia.org/wiki/Homomorphic_encryption

The title was fixed like 40 minutes ago, when you come back to old browser tabs you probably want to hit that reload button before leaving a comment ;)

Re: Codex starts encrypting sub-agent prompts

#109

Post by vbs_redlof »

jagged-chisel wrote: post #82
embedding-shape wrote: post #63

Earlier quoted context omitted.

The prompts are now encrypted, not just the transit connections...

Ok, so help me get this right: I ask the LLM for something, it generates prompts for sub-agents and sends them back to my client for it to call the sub-agents. Now, those sub-agent prompts are encrypted messages that the sub-agents will decrypt (by hitting a backend) to do their work. Might as well just stuff the prompts in a database and only hand back the primary key to the client to hand off to the sub-agents. Kee…

I imagine main agent tells subagent something along the lines of: use this tool on this local data with these instructions in ciphertext. Otherwise yeah, encryption would be redundant.

Re: Codex starts encrypting sub-agent prompts

#110

Post by anon373839 »

Outrageous yet predictable.

The only way these AI labs can get the app layer lock-in they need is if they can get customers used to writing them a blank check: “here, take my data and my system, do ‘stuff’ and bill me for it.”

Between this and the recent Grok upload breach, I consider these products radioactive.

Post reply on HN