It seems like they're doing something with the system prompt that I don't quite understand. I'm trying it in Claude Code and tool calls repeatedly show weird messages like "Not malware."
Never seen anything like that with other Anthropic models.
Claude Opus 4.7
371–380 of 1001 posts
Re: Claude Opus 4.7
#372This comment thread is a good learner for founders; look at how much anguish can be put to bed with just a little honest communication. 1. Oops, we're oversubscribed. 2. Oops, adaptive reasoning landed poorly / we have to do it for capacity reasons. 3. Here's how subscriptions work. Am I really writing this bullet point? As someone with a production application pinned on Opus 4.5, it is extremely difficult to tell ap…
These threads are always full of superstitious nonsense. Had a bad week at the AIs? Someone at Anthropic must have nerfed the model! The roulette wheel isn't rigged, sometimes you're just unlucky. Try another spin, maybe you'll do better. Or just write your own code.
Nah dude, that roulette wheel is 100% rigged. From top to bottom. No doubt about that. If you think they are playing fair you are either brand new to this industry, or a masochist.
Re: Claude Opus 4.7
#373Too late, personally after how bad 4.6 was the past week I was pushed to codex, which seems to mostly work at the same level from day to day. Just last night I was trying to get 4.6 to lookup how to do some simple tensor parallel work, and the agent used 0 web fetches and just hallucinated 17K very wrong tokens. Then the main agent decided to pretend to implement tp, and just copied the entire model to each node...
Same. I stopped my Pro subscription yesterday after entering the week with 70% of my tokens used by Monday morning (on light, small weekend projects, things I had worked on in the past and barely noticed a dent in usage.) Support was... unhelpful. It's been funny watching my own attitude to Anthropic change, from being an enthusiastic Claude user to pure frustration. But even that wasn't the trigger to leave, it was…
> It's been funny watching my own attitude to Anthropic change, from being an enthusiastic Claude user to pure frustration.
You were enthusiastic because it was a great product at an unsustainable price.
Its clear that Claude is now harnessing their model because giving access to their full model is too expensive for the $20/m that consumers have settled on as the price point they want to pay.
I wrote a more in depth analysis here, there's probably too much to meaningfully summarize in a comment: https://sustainableviews.substack.com/p/the-era-of-models-is...
Re: Claude Opus 4.7
#374> indeed, during its training we experimented with efforts to differentially reduce these capabilities
can't wait for the chinese models to make arrogant silicon valley irrelevant
Re: Claude Opus 4.7
#375I'm finding the "adaptive thinking" thing very confusing, especially having written code against the previous thinking budget / thinking effort / etc modes: https://platform.claude.com/docs/en/build-with-claude/adapti... Also notable: 4.7 now defaults to NOT including a human-readable reasoning token summary in the output, you have to add "display": "summarized" to get that: https://platform.claude.com/docs/en/build-…
Does this mean Claude no longer outputs the full raw reasoning, only summaries? At one point, exposing the LLM's full CoT was considered a core safety tenet.
I don't think it ever has. For a very long time now, the reasoning of Claude has been summarized by Haiku. You can tell because a lot of the times it fails, saying, "I don't see any thought needing to be summarised."
Re: Claude Opus 4.7
#376Earlier quoted context omitted.
Don't look at "thinking" tokens. LLMs sometimes produce thinking tokens that are only vaguely related to the task if at all, then do the correct thing anyways.
They also sometimes flag stuff in their reasoning and then think themselves out of mentioning it in the response, when it would actually have been a very welcome flag.
Yea I’ve seen this and stopped it and asked it about it.
Sometimes they notice bugs or issues and just completely ignore it.
Re: Claude Opus 4.7
#377Interestingly github-copilot is charging 2.5x as much for opus 4.7 prompts as they charged for opus 4.6 prompts (7.5x instead of 3x). And they're calling this "promotional pricing" which sounds a lot like they're planning to go even higher. Note they charge per-prompt and not per-token so this might in part be an expectation of more tokens per prompt. https://github.blog/changelog/2026-04-16-claude-opus-4-7-is-...
Not that anybody can actually use it though, as a large percentage of Copilot users are facing seemingly random multi-day rate limits.
https://www.theregister.com/2026/04/15/github_copilot_rate_l...
Re: Claude Opus 4.7
#378> Opus 4.7 uses an updated tokenizer that improves how the model processes text. The tradeoff is that the same input can map to more tokens—roughly 1.0–1.35× depending on the content type. caveman[0] is becoming more relevant by the day. I already enjoy reading its output more than vanilla so suits me well. [0] https://github.com/JuliusBrussee/caveman/tree/main
I find grep and common cli command spam to be the primary issue. I enjoy Rust Token Killer https://github.com/rtk-ai/rtk, and agents know how to get around it when it truncates too hard.
Re: Claude Opus 4.7
#379I think my results have actually become worse with Opus 4.7.
I have a pretty robust setup in place to ensure that Claude, with its degradations, ensures good quality. And even the lobotomized 4.6 from the last few days was doing better than 4.7 is doing right now at xhigh.
It's over-engineering. It is producing more code than it needs to. It is trying to be more defensible, but its definition of defensible seems to be shaky because it's landing up creating more edge cases. I think they just found a way to make it more expensive because I'm just gonna have to burn more tokens to keep it in check.
Re: Claude Opus 4.7
#380Too late, personally after how bad 4.6 was the past week I was pushed to codex, which seems to mostly work at the same level from day to day. Just last night I was trying to get 4.6 to lookup how to do some simple tensor parallel work, and the agent used 0 web fetches and just hallucinated 17K very wrong tokens. Then the main agent decided to pretend to implement tp, and just copied the entire model to each node...
Same. I stopped my Pro subscription yesterday after entering the week with 70% of my tokens used by Monday morning (on light, small weekend projects, things I had worked on in the past and barely noticed a dent in usage.) Support was... unhelpful. It's been funny watching my own attitude to Anthropic change, from being an enthusiastic Claude user to pure frustration. But even that wasn't the trigger to leave, it was…
I havent been using my claude sub lately but I liked 4.6 three weeks ago. Did something change?