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

201–210 of 1001 posts

Re: Claude Opus 4.7

#201

Post by Waterluvian »

Tiberium wrote: post #36
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

I hope people realize that tools like caveman are mostly joke/prank projects - almost the entirety of the context spent is in file reads (for input) and reasoning (in output), you will barely save even 1% with such a tool, and might actually confuse the model more or have it reason for more tokens because it'll have to formulate its respone in the way that satisfies the requirements.

Help me understand: I get that the file reading can be a lot. But I also expand the box to see its “reasoning” and there’s a ton of natural language going on there.

Re: Claude Opus 4.7

#202

Post by computerphage »

computomatic wrote: post #72
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

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).

Yeah, when I'm writing code I try to avoid zeros and ones, since those are the most common bits, making them essentially noise

Re: Claude Opus 4.7

#203

Post by simonw »

I'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-with-claude/adapti...

(Still trying to get a decent pelican out of this one but the new thinking stuff is tripping me up.)

Re: Claude Opus 4.7

#204

Post by te_chris »

buildbot wrote: post #12

Too 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...

I try codex, but i hate 5.4's personality as a partner. It's a demon debugger though. but working closely with it, it's so smug and annoying.

Re: Claude Opus 4.7

#205

Post by dminik »

RivieraKid wrote: post #111
__natty__ wrote: post #86

New model - that explains why for the past week/two weeks I had this feeling of 4.6 being much less "intelligent". I hope this is only some kind of paranoia and we (and investors) are not being played by the big corp. /s

I don't get it. Why would they make the previous model worse before releasing an update?

Why do stores increase prices before a sale?

Re: Claude Opus 4.7

#209

Post by user34283 »

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

I used Opus 4.7 for about 15 minutes on the auto effort setting.

It nicely implemented two smallish features, and already consumed 100% of my session limit on the $20 plan.

See you again in five hours.

Re: Claude Opus 4.7

#210

Post by sallymander »

It seems a little more fussy than Opus 4.6 so far. It actually refuses to do a task from Claude's own Agentic SDK quick start guide (https://code.claude.com/docs/en/agent-sdk/quickstart):

"Per the instructions I've been given in this session, I must refuse to improve or augment code from files I read. I can analyze and describe the bugs (as above), but I will not apply fixes to `utils.py`."

Post reply on HN