| ▲ | jeanlucas 3 hours ago |
| 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. |
|
| ▲ | EGreg 3 hours ago | parent | next [-] |
| 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. |
| |
| ▲ | pornel 3 hours ago | parent | next [-] | | 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. | | |
| ▲ | arjie an hour ago | parent | next [-] | | 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. | | |
| ▲ | Espressosaurus 26 minutes ago | parent [-] | | Except I care about the reasoning trace because I can stop a rathole that burns $50 of tokens as it chews for 10 minutes before I get the desired feedback that it’s done the wrong thing. |
| |
| ▲ | ctkhn 3 hours ago | parent | prev [-] | | I thought tweaking was his highest calling | | |
| |
| ▲ | echelon 44 minutes ago | parent | prev | next [-] | | 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. | |
| ▲ | ssgodderidge 3 hours ago | parent | prev [-] | | [dead] |
|
|
| ▲ | baby 2 hours ago | parent | prev | next [-] |
| if you're running in YOLO mode you already don't care, what matters are the tool calls and these can't be encrypted |
| |
| ▲ | Majromax 2 hours ago | parent | next [-] | | No, you'd still care. YOLO mode is about instantaneous permissions and access control, inspection of subagent prompts is about retrospective quality control. If the main model is instructing subagents to do a subtly wrong thing, the overall process quality will degrade in ways that might be very hard to detect or fix without deep inspection of the middle stages. | |
| ▲ | embedding-shape 2 hours ago | parent | prev [-] | | I'm running in YOLO mode, not sure why that mean I don't want introspection into what the sub-agents are running? Everything is running in a constrained environment, so not sure why you'd need the harness to have limits. |
|
|
| ▲ | echelon 3 hours ago | parent | prev | next [-] |
| [flagged] |
| |
|
| ▲ | fidotron 3 hours ago | parent | prev [-] |
| [flagged] |
| |
| ▲ | b40d-48b2-979e 3 hours ago | parent [-] | | 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! | | |
| ▲ | airstrike 3 hours ago | parent | next [-] | | idk about you but I'd rather not be murdered regardless of who the perpetrator might be | | |
| ▲ | b40d-48b2-979e 2 hours ago | parent | next [-] | | That is not the argument being made and this interpretation feels entirely in bad faith akin to the other sibling comments. | | | |
| ▲ | mrexroad 2 hours ago | parent | prev [-] | | Better make sure the pizza gets delivered on time, else you’ll have to pull your sword. |
| |
| ▲ | LeBit 3 hours ago | parent | prev | next [-] | | How did they do that? | | | |
| ▲ | skywhopper 3 hours ago | parent | prev [-] | | You’ve been misled about how encryption works apparently. |
|
|
