Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Opus 4.7

anthropic.com

Post reply on HN
Print view View original

991–1000 of 1001 posts

Re: Claude Opus 4.7

#991

Post by throwatdem12311 »

silverwind wrote: post #761
throwatdem12311 wrote: post #698

Holy moly it’s slow. An implement step for a simple delete entity endpoint in my rails app took 30 minutes. Nothing crazy but it had a couple checks it needed to do first. Very simple stuff like checking what the scheduled time is for something and checking the current status of a state machine. I’m tempted to switch back to Opus 4.6 and have it try again for reference because holy moly it legit felt way slower than…

Slow is good thought, that's when you know it'll get it right.

Correctness does not necessitate slowness.

And why would I want a slower mode that gets it right when the faster model already got it right before?

If it can’t even do basic stuff anymore I’m not gonna use it for advanced tasks either.

Re: Claude Opus 4.7

#993

Post by alblez »

coreylane wrote: post #267

Looks completely broken on AWS Bedrock "errorCode": "InternalServerException", "errorMessage": "The system encountered an unexpected error during processing. Try your request again.",

same, I tried with claude code

Re: Claude Opus 4.7

#994

Post by Zavora »

coreylane wrote: post #267

Looks completely broken on AWS Bedrock "errorCode": "InternalServerException", "errorMessage": "The system encountered an unexpected error during processing. Try your request again.",

same error!

Re: Claude Opus 4.7

#996

Post by ojuschugh1 »

cupofjoakim wrote: post #20

> 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

try this - https://github.com/ojuschugh1/sqz

Re: Claude Opus 4.7

#997

Post by iinovv »

ramonga wrote: post #417
coreylane wrote: post #267

Looks completely broken on AWS Bedrock "errorCode": "InternalServerException", "errorMessage": "The system encountered an unexpected error during processing. Try your request again.",

I get this error too and if I try again: { ... "error":{"type":"permission_error","message":"anthropic.claude-opus-4-7 is not available for this account. You can explore other available models on Amazon Bedrock. For additional access options, contact AWS Sales at https://aws.amazon.com/contact-us/sales-support/ "}}

same here. have u found any solution?

Re: Claude Opus 4.7

#999

Post by owentbrown »

Is anyone else noticing that the benchmarks for Claude 4.7 don't specify the token window? Cursor, and LiteLLM at my company, limit the token window to 200k.

It feels like to me like 4.7 is not better, and is maybe worse than 4.6 when capped to 200k context window.

Does anyone have stats on performance of 4.6 vs. 4.7 when context window is capped at 200k?

Post reply on HN