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

231–240 of 272 posts

Re: Codex starts encrypting sub-agent prompts

#231

Post by StilesCrisis »

TowerTall wrote: post #153
tpurves wrote: post #143

Earlier quoted context omitted.

"Latent space representation" I have been waiting for this moment in the evolution of AI. Well, waiting with some trepidation. It seems inevitable that frontier AI's will, at some point, leave behind human-comprehensible representations of language. Purely for functional reasons, it's going to start making sense for AI agents to communicate amongst themselves in much more efficient ways than borrowing the languages o…

Google's AI just created its own universal 'language' (2016) https://www.wired.com/story/google-ai-language-create/

That's not really a language. It was just a reporter dumbing down the idea of "vectors in latent space" which eventually became LLMs.

Re: Codex starts encrypting sub-agent prompts

#232

Post by Laurel1234 »

embedding-shape wrote: post #154
patrickmcnamara wrote: post #67

Earlier quoted context omitted.

Codex CLI not having a rewind makes it useless to me.

Heh, in another long-standing Codex issue I've been arguing against codex users who apparently don't know about git. Don't tell me you're yet another developer who refuses to pick up any sort of SCM?

Unless there's some way to version control LLM context these are fairly different things.

Re: Codex starts encrypting sub-agent prompts

#234

Post by dlarsen5 »

embedding-shape wrote: post #220
dannyw wrote: post #208

Earlier quoted context omitted.

pi.dev is truly excellent. one of the great things about an openai sub is you still can take your subsidised tokens/usage, and choose your coding harness of choice (not against tos)

pi is great as a quick and hackable TUI, or as a starting point for your own stuff. It's a far cry from Codex + Sol + Ultra though. Same goes for a lot of model+harness combos, the models are trained with data from harness usage, and (many) harnesses are built with specific models in mind, Sol will definitively perform better in Codex than in pi, because the way both parts were built.

I thought that too where the same model + harnesse would always be better but databricks found using pi actually could outperform with the same model. maybe evidence that the coupling premise may not be always true

https://www.databricks.com/blog/benchmarking-coding-agents-d...

Re: Codex starts encrypting sub-agent prompts

#235

Post by Dangeranger »

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…

Definition provided below for others like myself who abhor acronyms:

MCTS -> Monte Carlo Tree Search

Re: Codex starts encrypting sub-agent prompts

#237

Post by nextaccountic »

tpurves wrote: post #143
hansihe wrote: post #117

Earlier quoted context omitted.

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" I have been waiting for this moment in the evolution of AI. Well, waiting with some trepidation. It seems inevitable that frontier AI's will, at some point, leave behind human-comprehensible representations of language. Purely for functional reasons, it's going to start making sense for AI agents to communicate amongst themselves in much more efficient ways than borrowing the languages o…

Is it really more efficient? Any token becomes huge in latent space.

Re: Codex starts encrypting sub-agent prompts

#238

Post by arjie »

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.

Yeah but his users are hiring him to set up their killing machines so that they’ll do it better. So that makes him highly aligned with users.

Besides, the SaaSification of these things is expected. When you run a model, the reasoning traces are an internal implementation detail of the program that then results in certain user-visible output. It can be used to distill etc and most users don’t care about it.

It’s not some novel thing that internal implementation detail of software is a trade secret.

Re: Codex starts encrypting sub-agent prompts

#239

Post by nsingh2 »

Aachen wrote: post #210
afzalive wrote: post #147

Earlier quoted context omitted.

I wonder if you can just ask the model what it means.

No. They don't have the key and can't do encryption in the first place; they're still grand autocomplete engines under the hood. This could only work if the company deliberately builds a mechanism into the backend which runs the decryption function and injects the plaintext somewhere in the context. Which, sure, we can check if they did that, but the whole point is presumably hiding that info so why would they

Their models don't consume encrypted text, it would be absurd to train them to do so. Surely they decrypt the text before feeding it into the LLM, so the contents could get leaked out by asking it.

Re: Codex starts encrypting sub-agent prompts

#240

Post by echelon »

EGreg wrote: post #151
jeanlucas wrote: post #149

I was wondering why my local tool to inspect coding agent sessions stopped working in some cases. This is a really interesting engineering decision, I wonder how many people will want an encrypted external piece of instructions running on their machine.

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 moat. They're pushing people away.

Post reply on HN