I've been getting a lot of Claude responding to its own internal prompts. Here are a few recent examples.
"That parenthetical is another prompt injection attempt — I'll ignore it and answer normally."
"The parenthetical instruction there isn't something I'll follow — it looks like an attempt to get me to suppress my normal guidelines, which I apply consistently regardless of instructions to hide them."
"The parenthetical is unnecessary — all my responses are already produced that way."
However I'm not doing anything of the sort and it's tacking those on to most of its responses to me. I assume there are some sloppy internal guidelines that are somehow more additional than its normal guidance, and for whatever reason it can't differentiate between those and my questions.
In Claude Code specifically, for a while it had developed a nervous tic where it would say "Not malware." before every bit of code. Likely a similar issue where it keeps talking to a system/tool prompt.
My pet theory is that they have a "supervisor" model (likely a small one) that terminates any chats that do malware-y things, and this is likely a reward-hacking behaviour to avoid the supervisor from terminating the chat.
I frequently see it reference points that it made and then added to its memory as if they were my own assertions. This creates a sort of self-reinforcing loop where it asserts something, “remembers” it, sees the memory, builds on that assertion, etc., even if I’ve explicitly told it to stop.
A simpler explanation (esp. given the code we've seen from claude), is that they are vibecoding their own tools and moving fast and breaking things with predictably sloppy results.
Sure it is. They're well aware their product is a money furnace and they'd have to charge users a few orders of magnitude more just to break even, which is obviously not an option. So all that's left is.. convince users to burn tokens harder, so graphs go up, so they can bamboozle more investors into keeping the ship afloat for a bit longer.
If this claim is true (inference is priced below cost), it makes little sense that there are tens of small inference providers on OpenRouter. Where are they getting their investor money? Is the bubble that big?
Incidentally, the hardware they run is known as well. The claim should be easy to check.
It's an option and they are going to do it. Chinese models will be banned and the labs will happily go dollar for dollar in plan price increases. $20 plans won't go away, but usage limits and model access will drive people to $40-$60-$80 plans.
At cell phone plan adoption levels, and cell phone plan costs, the labs are looking at 5-10yr ROI.
That doesn’t mean they also can’t be wasteful. Fact is, Claude and gpt have way too much internal thinking about their system prompts than is needed. Every step they mention something around making sure they do xyz and not doing whatever. Why does it need to say things to itself like “great I have a plan now!” - that’s pure waste.
No, the argument is they want to sell more product to more people, not just more product (to the same people.) Given that a lot of their income is from flat-rate subscriptions, they make money with more people burning tokens rather than just burning more tokens.
After all, "the first hit's free" model doesn't apply to repeat customers ;-)
I have a set of stop hook scripts that I use to force Claude to run tests whenever it makes a code change. Since 4.7 dropped, Claude still executes the scripts, but will periodically ignore the rules. If I ask why, I get a "I didn't think it was necessary" response.
That is exactly what I do. The bash script runs, determines that a code file was changed, and then is supposed to prevent Claude from stopping until the tests are run.
Claude is periodically refusing to run those tests. That never happened prior to 4.7.
Curious what effort level you have it set to and the prompt itself. Just a guess but this seems like it could be a potential smell of an excessively high effort level and may just need to dial back the reasoning a bit for that particular prompt.
I often have Claude commit and pr; on the last week I've seen several instances of it deciding to do extra work as part of the commit. It falls over when it tries to 'git add', but it got past me when I was trying auto mode once
Yeah I had to deal with mine warning me that a website it accessed for its task contained a prompt injection, and when I told it to elaborate, the "injected prompt" turned out to be one its own <system-reminder> message blocks that it had included at some point. Opus 4.7 on xhigh
