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

Claude Sonnet 4.6

anthropic.com

Post reply on HN
Print view View original

361–370 of 1001 posts

Re: Claude Sonnet 4.6

#361

Post by drcongo »

SatvikBeri wrote: post #351
wongarsu wrote: post #341

Earlier quoted context omitted.

Keep in mind that the people who experience issues will always be the loudest. I've overall enjoyed 4.6. On many easy things it thinks less than 4.5, leading to snappier feedback. And 4.6 seems much more comfortable calling tools: it's much more proactive about looking at the git history to understand the history of a bug or feature, or about looking at online documentation for APIs and packages. A recent claude code…

I've also seen Opus 4.6 as a pure upgrade. In particular, it's noticeably better at debugging complex issues and navigating our internal/custom framework.

Same here. 4.6 has been considerably more dilligent for me.

Re: Claude Sonnet 4.6

#362

Post by Gracana »

grav wrote: post #278
andrewchilds wrote: post #244

Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.

I fail to understand how two LLMs would be "consuming" a different amount of tokens given the same input? Does it refer to the number of output tokens? Or is it in the context of some "agentic loop" (eg Claude Code)?

They're talking about output consuming from the pool of tokens allowed by the subscription plan.

Re: Claude Sonnet 4.6

#363

Post by charcircuit »

andsoitis wrote: post #276
timpera wrote: post #102

Earlier quoted context omitted.

Which plan did you choose? I am subscribed to both and would love to stick with Claude only, but Claude's usage limits are so tiny compared to ChatGPT's that it often feels like a rip-off.

Pro. At $17 per month, it is cheaper than ChatGPT's $20. I've just switched so haven't run into constraints yet.

Claude Pro is $20/mo if you do not lock in for a year long contract.

Re: Claude Sonnet 4.6

#364

Post by ctoth »

andrewchilds wrote: post #244

Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.

For me it's the ... unearned confidence that 4.5 absolutely did not have?

I have a protocol called "foreman protocol" where the main agent only dispatches other agents with prompt files and reads report files from the agents rather than relying on the janky subagent communication mechanisms such as task output.

What this has given me also is a history of what was built and why it was built, because I have a list of prompts that were tasked to the subagents. With Opus 4.5 it would often leave the ... figuring out part? to the agents. In 4.6 it absolutely inserts what it thinks should happen/its idea of the bug/what it believes should be done into the prompt, which often screws up the subagent because it is simply wrong and because it's in the prompt the subagent doesn't actually go look. Opus 4.5 would let the agent figure it out, 4.6 assumes it knows and is wrong

Re: Claude Sonnet 4.6

#365

Post by cheema33 »

andrewchilds wrote: post #244

Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.

> Many people have reported Opus 4.6 is a step back from Opus 4.5.

Many people say many things. Just because you read it on the Internet, doesn't mean that it is true. Until you have seen hard evidence, take such proclamations with large grains of salt.

Re: Claude Sonnet 4.6

#366

Post by dakolli »

andrewchilds wrote: post #244

Many people have reported Opus 4.6 is a step back from Opus 4.5 - that 4.6 is consuming 5-10x as many tokens as 4.5 to accomplish the same task: https://github.com/anthropics/claude-code/issues/23706 I haven't seen a response from the Anthropic team about it. I can't help but look at Sonnet 4.6 in the same light, and want to stick with 4.5 across the board until this issue is acknowledged and resolved.

I called this many times over the last few weeks on this website (and got downvoted every time), that the next generation of models would become more verbose, especially for agentic tool calling to offset the slot machine called CC's propensity to light the money on fire that's put into it.

At least in vegas they don't pour gasoline on the cash put into their slot machines.

Re: Claude Sonnet 4.6

#367

Post by giancarlostoro »

WarmWash wrote: post #317
giancarlostoro wrote: post #184

Earlier quoted context omitted.

They blanket banned any AI stuff that's not pre-approved. If I go to chatgpt.com it asks me if I'm sure. I wish they had not banned Claude unfortunately when they were evaluating LLMs I wasn't using Claude yet so I couldnt pipe up. I only use ChatGPT free tier and to ask things that I can't find on Google because Google made their search engine terrible over the years.

Google's AI mode search is gemini 3, not the AI overview model. It's decent and gives you more than chatgpt free.

I don't want Google's model though, I just want Claude.

Re: Claude Sonnet 4.6

#368

Post by ahtihn »

energy123 wrote: post #118
andsoitis wrote: post #77

I’m voting with my dollars by having cancelled my ChatGPT subscription and instead subscribing to Claude. Google needs stiff competition and OpenAI isn’t the camp I’m willing to trust. Neither is Grok. I’m glad Anthropic’s work is at the forefront and they appear, at least in my estimation, to have the strongest ethics.

Grok usage is the most mystifying to me. Their model isn't in the top 3 and they have bad ethics. Like why would anyone bother for work tasks.

The lack of ethics is a selling point.

Why anyone would want a model that has "safety" features is beyond me. These features are not in the user's interest.

Re: Claude Sonnet 4.6

#369

Post by simianwords »

malfist wrote: post #235
stevepike wrote: post #87

I'm a bit surprised it gets this question wrong (ChatGPT gets it right, even on instant). All the pre-reasoning models failed this question, but it's seemed solved since o1, and Sonnet 4.5 got it right. https://claude.ai/share/876e160a-7483-4788-8112-0bb4490192af This was sonnet 4.6 with extended thinking.

Chatgpt doesn't get it right: https://chatgpt.com/share/6994c312-d7dc-800f-976a-5e4fbec0ae... ``` Use digit concatenation plus addition: 888 + 88 + 8 + 8 + 8 = 1000 Digit count: 888 → three 8s 88 → two 8s 8 + 8 + 8 → three 8s Total: 3 + 2 + 3 = 9 eights Operation used: addition only ``` Love the 3 + 2 + 3 = 9

chatgpt gets it right. maybe you are using free or non thinking version?

https://chatgpt.com/share/6994d25e-c174-800b-987e-9d32c94d95...

Re: Claude Sonnet 4.6

#370

Post by bearjaws »

Danielopol wrote: post #316

It excels at agentic knowledge work. These custom, domain-specific playbooks are tailor made: claudecodehq.com

Is there a playbook to center-align the content on the site? On 1440p Firefox and Chrome its all left aligned.
Post reply on HN