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

Claude Opus 4.6

anthropic.com

Post reply on HN
Print view View original

81–90 of 1001 posts

Re: Claude Opus 4.6

#81

Post by neuronexmachina »

pjot wrote: post #62

Claude Code release notes: > Version 2.1.32: • Claude Opus 4.6 is now available! • Added research preview agent teams feature for multi-agent collaboration (token-intensive feature, requires setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1) • Claude now automatically records and recalls memories as it works • Added "Summarize from here" to the message selector, allowing partial conversation summarization. • Skills defi…

> Claude now automatically records and recalls memories as it works

Neat: https://code.claude.com/docs/en/memory

I guess it's kind of like Google Antigravity's "Knowledge" artifacts?

Re: Claude Opus 4.6

#82

Post by raincole »

blibble wrote: post #17

> We build Claude with Claude. Our engineers write code with Claude Code every day well that explains quite a bit

It explains how important dogfooding is if you want to make an extremely successful product.

Re: Claude Opus 4.6

#83

Post by blibble »

jama211 wrote: post #71
blibble wrote: post #17

> We build Claude with Claude. Our engineers write code with Claude Code every day well that explains quite a bit

It’s extremely successful, not sure what it explains other than your biases

Microsoft's products are also extremely successful

they're also total garbage

Re: Claude Opus 4.6

#84

Post by SubiculumCode »

apetresc wrote: post #61

Impressive that they publish and acknowledge the (tiny, but existent) drop in performance on SWE-Bench Verified between Opus 4.5 to 4.6. Obviously such a small drop in a single benchmark is not that meaningful, especially if it doesn't test the specific focus areas of this release (which seem to be focused around managing larger context). But considering how SWE-Bench Verified seems to be the tech press' favourite be…

Isn't SWE-Bench Verified pretty saturated by now?

Re: Claude Opus 4.6

#85

Post by tgtweak »

jsheard wrote: post #38
blibble wrote: post #17

> We build Claude with Claude. Our engineers write code with Claude Code every day well that explains quite a bit

CC has >6000 open issues, despite their bot auto-culling them after 60 days of inactivity. It was ~5800 when I looked just a few days ago so they seem to be accelerating towards some kind of bug singularity.

plot twist, it's all claude code instances submitting bug reports on behalf of end users.

Re: Claude Opus 4.6

#86

Post by lufenialif2 »

3abiton wrote: post #55
Someone1234 wrote: post #19

Does anyone with more insight into the AI/LLM industry happen to know if the cost to run them in normal user-workflows is falling? The reason I'm asking is because "agent teams" while a cool concept, it largely constrained by the economics of running multiple LLM agents (i.e. plans/API calls that make this practical at scale are expensive). A year or more ago, I read that both Anthropic and OpenAI were losing money o…

It's not just that. Everyone is complacent with the utilization of AI agents. I have been using AI for coding for quite a while, and most of my "wasted" time is correcting its trajectory and guiding it through the thinking process. It's very fast iterations but it can easily go off track. Claude's family are pretty good at doing chained task, but still once the task becomes too big context wise, it's impossible to ge…

Cost wise, doesn’t that depend on what you could be doing besides steering agents?

Re: Claude Opus 4.6

#87

Post by romanovcode »

CryptoBanker wrote: post #63
minimaxir wrote: post #23

Will Opus 4.6 via Claude Code be able to access the 1M context limit? The cost increase by going above 200k tokens is 2x input, 1.5x output, which is likely worth it especially for people with the $100/$200 plans.

The 1M context is not available via subscription - only via API usage

Well this is extremely disappointing to say the least.

Re: Claude Opus 4.6

#90

Post by tgtweak »

legitster wrote: post #72

I'm still not sure I understand Anthropic's general strategy right now. They are doing these broad marketing programs trying to take on ChatGPT for "normies". And yet their bread and butter is still clearly coding. Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the depth of research, the type of tasks it can handle, and the qual…

Claude itself (outside of code workflows) actually works very well for general purpose chat. I have a few non-technical friends that have moved over from chatgpt after some side-by-side testing and I've yet to see one go back - which is good since claude circa 8 months ago was borderline unusable for anything but coding on the api.
Post reply on HN