211–220 of 325 posts
Interestingly, I didn't have to drop to a dumber model, just a 2 sentence prompt auto-injected before and after compaction made all their models output the encrypted compaction data in plaintext.
The result was... interesting. There's nothing unique in there and I still don't understand why they decided to encrypt it in the first place.
I did this with Codex's recent encryption of compaction. Interestingly, I didn't have to drop to a dumber model, just a 2 sentence prompt auto-injected before and after compaction made all their models output the encrypted compaction data in plaintext. The result was... interesting. There's nothing unique in there and I still don't understand why they decided to encrypt it in the first place.
I did this with Codex's recent encryption of compaction. Interestingly, I didn't have to drop to a dumber model, just a 2 sentence prompt auto-injected before and after compaction made all their models output the encrypted compaction data in plaintext. The result was... interesting. There's nothing unique in there and I still don't understand why they decided to encrypt it in the first place.
Possibly something to do with other providers using the it to train their own models?
There's nothing to gain from this, really. Perhaps they're preparing for something in the future, where they could give the model server-side tools that improves summarization, but right now, it's just a simple prompt.
Earlier quoted context omitted.
Correct, yes. It’s delightedly simple. And they validate by asserting the reasoning token length matches
For all of the years of research, thinking and talking about model alignment, safety, confinement, etc, when it comes down to it these companies appear to be entirely incompetent.
"Stealing" something you already paid for (tokens), but that you can't have access to(!). And trained on the sum of human knowledge. Training on other model outputs ought to be business as usual, stop using morally charged terms made up by future monopolists: https://thomasdullien.github.io/posts/2026-06-15-rl-economic...
> stop using morally charged terms made up by future monopolists Lets not gloss over this claim. Being: “Stealing is a morally charged term made up by future monopolists.” I strongly disagree. Stealing is not a made up term and property rights are foundational for any society. Your take is at least sensationalist if not malicious.
"Stealing" something you already paid for (tokens), but that you can't have access to(!). And trained on the sum of human knowledge. Training on other model outputs ought to be business as usual, stop using morally charged terms made up by future monopolists: https://thomasdullien.github.io/posts/2026-06-15-rl-economic...
The only person calling it stealing is the author of this article, so this is a pointless discussion. The majority of this thread is just arguing with themselves.
Earlier quoted context omitted.
No I didn't. I buy my tokens from a provider that exposes the model reasoning so I can understand what it's doing and work with it, or interrupt if I see things going in the wrong direction.
I agree with you in principle. I'm just pointing out that the latter is in some way another valid point of view.
If I was being charged for the raw, output/input token count, excluding thinking/reasoning token costs, then sure. But at least via the API, you pay for tokens you cannot see.
Earlier quoted context omitted.
I agree with you in principle. I'm just pointing out that the latter is in some way another valid point of view.
Thinking tokens aren't free though. This is not a valid point of view. If I was being charged for the raw, output/input token count, excluding thinking/reasoning token costs, then sure. But at least via the API, you pay for tokens you cannot see.
There are features of input and output that are opaque to you, but that you pay for. Part of how model providers chose to run their service.
Earlier quoted context omitted.
It isn’t the concern of the LLM. Regardless of where the encryption/decryption is happening, the issue is that the LLM needs to access the raw CoT.
Again I don’t think you’re really getting at what I am asking. Sorry. My whole point was why does the LLM have access of decrypting. It should happen outside of the LLM layer.