I've taken a two week hiatus on my personal projects, so I haven't experienced any of the issues that have been so widely reported recently with CC. I am eager to get back and see if experience these same issues.
Claude Opus 4.7
591–600 of 1001 posts
Re: Claude Opus 4.7
#592It 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.
there's a line inside claude code mentioning to care about this. combined with new stronger instruction following behavior, you're going to be seeing it a lot unless you patch it out. or wait for a fix.
Re: Claude Opus 4.7
#593If the model is based on a new tokenizer, that means that it's very likely a completely new base model. Changing the tokenizer is changing the whole foundation a model is built on. It'd be more straightforward to add reasoning to a model architecture compared to swapping the tokenizer to a new one. Usually a ground up rebuild is related to a bigger announcement. So, it's weird that they'd be naming it 4.7. Swapping o…
Mm, don't you just need to retrain the embedding layer for the new tokenizer? I agree it seems likely this is like a stopgap new model release or a distillation of mythos or something while they get a better mythos release in place. But there are some things that look really different than mythos in the model card, e.g. the number of tokens it uses at different effort levels.
Maybe it's an abandoned candidate "5.0" model that mythos beat out.
Re: Claude Opus 4.7
#594They've increased their cybersecurity usage filters to the point that Opus 4.7 refuses to work on any valid work, even after web fetching the program guidelines itself and acknowledging "This is authorized research under the [Redacted] Bounty program, so the findings here are defensive research outputs, not malware. I'll analyze and draft, not weaponize anything beyond what's needed to prove the bug to [Redacted]. I…
Having tried codex for some security practice, it is similarly terrible.
You can link it to a course page that features the example binary to download, it can verify the hash and confirm you are working with the same binary - and then it refuses to do any practical analysis on it
Re: Claude Opus 4.7
#595I'm an Opus fanboy, but this is literally the worst coding model I have used in 6 months. Its completely unusable and borderline dangerous. It appears to think less than haiku, will take any sort of absurd shortcut to achieve its goal, refuses to do any reasoning. I was back on 4.6 within 2 hours.
Did Anthropic just give up their entire momentum on this garbage in an effort to increase profitability?
Re: Claude Opus 4.7
#596Quick everyone to your side projects. We have ~3 days of un-nerfed agentic coding again.
Clearly you didn't try it yet ;)
Re: Claude Opus 4.7
#597> 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
On my private internal oil and gas benchmark, I found a counterintuitive result. Opus 4.7 scores 80%, outperforming Opus 4.6 (64%) and GPT-5.4 (76%). But it's the cheapest of the three models by 2x.
This is mainly driven by reduced reasoning token usage. It goes to show that "sticker price" per token is no longer adequate for comparing model cost.
Re: Claude Opus 4.7
#598I'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-…
If you do include reasoning tokens you pay more, right?
Re: Claude Opus 4.7
#599This 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.
It's also difficult to recognize that when it got it right THAT might have been the lucky week.
Re: Claude Opus 4.7
#600Serious question about using Claude for coding. I maintain a couple of small opensource applications written in python that I created back in 2014/2015. I have used Claude Code to improve one of my projects with features I have wanted for a long time but never really had the time to do. The only way I felt comfortable using Claude Code was holding its hand through every step, doing test driven changes and manually reviewing the code afterwards. Even on small code bases it makes a lot of mistakes. There no way I would just tell it to go wild without even understanding what they are doing and I can't help but think that massive code bases that have moved to vibe coding are going to spend inordinate amounts of time testing and auditing code, or at worst just ship often and fix later.
I am just an amateur hobbyist, but I was dumbfounded how quickly I can create small applications. Humans are lazy though and I can't help but feel we are being inundated with sketchy apps doing all kinds of things the authors don't even understand. I am not anti AI or anything, I use it and want to be comfortable with it, but something just feels off. It's too easy to hand the keys over to Claude and not fully disclose to others whats going on. I feel like the lack of transparency leads to suspicion when anyone talks about this or that app they created, you have to automatically assume its AI and there is a good chance they have no clue what they created.