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

251–260 of 272 posts

Re: Codex starts encrypting sub-agent prompts

#251

Post by radicality »

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…

That’s actually what got me to switch and use Codex sometime beginning this year, the compaction via these encrypted blobs was just waaaay better than Claude. I had short convos with Claude where it would forget something very obvious and important few million tokens into a task, whereas I reached ~1B tokens in some local codex sessions and it was recalling and paying attention to things I mentioned way back at the beginning of the session (and not persisted anywhere else in the repo/md files etc)

Re: Codex starts encrypting sub-agent prompts

#252

Post by braebo »

embedding-shape wrote: post #65
resonious wrote: post #61

I guess this implies that non-Codex harnesses get a little bit worse? In wondering what's so special about their subagents system that they feel the need to hide these messages...

Sol and Terra seems specifically post-trained to handle multi-agent orchestration, I'm guessing OpenAI feels like the trained data of when to do the spawning and what context to include for the new sub-agent is the magic in their new models, so that's what they're aiming to preserve. But, this is all a guess of course.

It’s funny because Sol sucks at using subagents effectively. It’s very dumb and makes terrible decisions constantly.

Re: Codex starts encrypting sub-agent prompts

#253

Post by EGreg »

echelon wrote: post #240
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.

I think there are OpenAI / Anthropic employees in here flagging comments: https://news.ycombinator.com/item?id=48907099 These companies are behaving against the best interests of their customers. Both OpenAI and Anthropic should be ashamed. These companies' products are awesome, but the way they conduct business is scummy. They must be worried there is no moat. If they keep up this behavior, there truly will be no mo…

It’s not about the companies specifically, or even AI specifically, but the incentive structure. I think the issue is more that they are embedded in a system of competition, where they can’t afford not to do things to “win” and fend off competitors’ practices. The people in the companies feel and understand this better than anyone.

I think Anthropic, being a Public Benefit Corporation, can absolutely do better than OpenAI. OpenAI was a nonprofit but flipped. Many people left from OpenAI to Anthropic, I think all original founders of Anthropic are still with Anthropic.

We have seen the same things in Web2 and Web3, this is not at all unique to AI companies! How many people at HN went to work for Facebook, or Google etc? The “don’t be evil” motto is nice but when you have to compete, you often end up doing the things you think you didn’t have to do.

With Web2 the stakes were: “centrally controlling speech”. With Web3 the stakes were: “people lose programmable money they gambled with”. With AI the stakes are much bigger. This isn’t about a company being moral or not. This is about incentives of the broader ecosystem, and how the products are designed.

As long as people (like Kevin O’Leary) say “but are you going to just let China pull ahead of us” we’re all going to be in a race (to the bottom, for a lot of affected people). It isn’t about OpenAI or Anthropic specifically. Hate the game, not the player.

It doesn’t have to be this way. The game can change: https://safebots.ai/singularity.html

Re: Codex starts encrypting sub-agent prompts

#254

Post by ATMLOTTOBEER »

next_xibalba wrote: post #205
ATMLOTTOBEER wrote: post #176

Earlier quoted context omitted.

Can you not abuse “mcts” as a buzzword like this The thing you’re gesturing at isn’t mcts in any real sense

You could replace “gesturing at” with “describing,” then explain why the description is technically wrong.

No thanks

Re: Codex starts encrypting sub-agent prompts

#256

Post by flexagoon »

skeledrew wrote: post #123
flexagoon wrote: post #13

Ah I was wondering why the Chinese black market resellers stopped working yesterday, I guess that's it

Interesting. Got a link for this?

For what? I was using GPT-5.5 through Byesu.com and it suddenly stopped working yesterday

(Not affiliated in any way, I'm sure there are better services out there, this is just the one a friend recommended to me and I haven't researched other options)

Re: Codex starts encrypting sub-agent prompts

#258

Post by embedding-shape »

binyu wrote: post #257
embedding-shape wrote: post #138

Earlier quoted context omitted.

Bingo!

As in "browser"? or the literal thing?

I mean, yeah. At this point you made me think way more about this than I thought I would. I guess either works, whatever floats your boat :)

Re: Codex starts encrypting sub-agent prompts

#259

Post by airstrike »

b40d-48b2-979e wrote: post #188
airstrike wrote: post #175

Earlier quoted context omitted.

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

That is not the argument being made and this interpretation feels entirely in bad faith akin to the other sibling comments.

it is 100% the argument being made, but you can't see it just yet
Post reply on HN