> In Claude Code, we’ve raised the default effort level to xhigh for all plans.
Does it also mean faster to getting our of credits?
Claude Opus 4.7
71–80 of 1001 posts
Re: Claude Opus 4.7
#72> 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 was doing some experiments with removing top 100-1000 most common English words from my prompts. My hypothesis was that common words are effectively noise to agents. Based on the first few trials I attempted, there was no discernible difference in output. Would love to compare results with caveman.
Caveat: I didn’t do enough testing to find the edge cases (eg, negation).
Re: Claude Opus 4.7
#73Is Codex the new goto? Opus stopped being useful about 45-60 days ago.
Re: Claude Opus 4.7
#74Too 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...
so even with a new tokenizer that can map to more tokens than before, their answer is still just "you're not managing your context well enough"
"Opus 4.7 uses an updated tokenizer that [...] can map to more tokens—roughly 1.0–1.35× depending on the content type.
[...]
Users can control token usage in various ways: by using the effort parameter, adjusting their task budgets, or prompting the model to be more concise."
Re: Claude Opus 4.7
#75> First, Opus 4.7 uses an updated tokenizer that improves how the model processes text
wow can I see it and run it locally please? Making API calls to check token counts is retarded.
Re: Claude Opus 4.7
#76> during its training we experimented with efforts to differentially reduce these capabilities
> We are releasing Opus 4.7 with safeguards that automatically detect and block requests that indicate prohibited or high-risk cybersecurity uses.
Ah f... you!
Re: Claude Opus 4.7
#77Too 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...
Until the next time they push you back to Claude. At this point, I feel like this has to be the most unstable technology ever released. Imagine if docker had stopped working every two releases
Re: Claude Opus 4.7
#78Earlier quoted context omitted.
They don't have enough compute for all their customers. OpenAI bet on more compute early on which prompted people to say they're going to go bankrupt and collapse. But now it seems like it's a major strategic advantage. They're 2x'ing usage limits on Codex plans to steal CC customers and it seems to be working. It seems like 90% of Claude's recent problems are strictly lack of compute related.
Honestly, I personally would rather a time-out than the quality of my response noticably downgrading. I think what I found especially distrustful is the responses from employees claiming that no degredation has occured. An honest response of "Our compute is busy, use X model?" would be far better than silent downgrading.
Are they convinced that claiming they have technical issues while continuing to adjust their internal levers to choose which customers to serve is holistically the best path?
Re: Claude Opus 4.7
#79I just subscribed this month again because I wanted to have some fun with my projects. Tried out opus 4.6 a bit and it is really really bad. Why do people say it's so good? It cannot come up with any half-decent vhdl. No matter the prompt. I'm very disappointed. I was told it's a good model
And yet another "AI doesn't work" comment without any meaningful information. What were your exact prompts? What was the output?
This is like a user of conventional software complaining that "it crashes", without a single bit of detail, like what they did before the crash, if there was any error message, whether the program froze or completely disappeared, etc.
Re: Claude Opus 4.7
#80> We are releasing Opus 4.7 with safeguards that automatically detect and block requests that indicate prohibited or high-risk cybersecurity uses.
Fucking hell.
Opus was my go-to for reverse engineering and cybersecurity uses, because, unlike OpenAI's ChatGPT, Anthropic's Opus didn't care about being asked to RE things or poke at vulns.
It would, however, shit a brick and block requests every time something remotely medical/biological showed up.
If their new "cybersecurity filter" is anywhere near as bad? Opus is dead for cybersec.