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

411–420 of 1001 posts

Re: Claude Sonnet 4.6

#411

Post by nwienert »

DaKevK wrote: post #396
ctoth wrote: post #364

Earlier quoted context omitted.

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 p…

Have you tried framing the hypothesis as a question in the dispatch prompt rather than a statement? Something like -- possible cause: X, please verify before proceeding -- instead of stating it as fact. Might break the assumption inheritance without changing the overall structure.

After a month of obliterating work with 4.5, I spent about 5 days absolutely shocked at how dumb 4.6 felt, like not just a bit worse but 50% at best. Idk if it's the specific problems I work on but GP captured it well - 4.5 listened and explored better, 4.6 seems to assume (the wrong thing) constantly, I would be correcting it 3-4 times in a row sometimes. Rage quit a few times in the first day of using it, thank god I found out how to dial it back.

Re: Claude Sonnet 4.6

#412

Post by svachalek »

ceroxylon wrote: post #132
crummy wrote: post #49

Earlier quoted context omitted.

Opus is supposed to be the expensive-but-quality one, while Sonnet is the cheaper one. So if you don't want to pay the significant premium for Opus, it seems like you can just wait a few weeks till Sonnet catches up

Strangely enough, my first test with Sonnet 4.6 via the API for a relatively simple request was more expensive ($0.11) than my average request to Opus 4.6 (~$0.07), because it used way more tokens than what I would consider necessary for the prompt.

This is an interesting trend with recent models. The smarter ones get away with a lot less thinking tokens, partially to fully negating the speed/price advantage of the smaller models.

Re: Claude Sonnet 4.6

#413

Post by patapong »

Gigachad wrote: post #406
raincole wrote: post #254

Earlier quoted context omitted.

The real interesting part is how often you see people on HN deny this. People have been saying the token cost will 10x, or AI companies are intentionally making their models worse to trick you to consume more tokens. As if making a better model isn't not the most cutting-throat competition (probably the most competitive market in the human history) right now.

Only until the music stops. Racing to give away the most stuff for free can only last so long. Eventually you run out of other people’s money.

Uber managed to make it work for quite a while

Re: Claude Sonnet 4.6

#414

Post by nsxwolf »

WarmWash wrote: post #266
gordonhart wrote: post #90

Earlier quoted context omitted.

Remember when GPT-2 was “too dangerous to release” in 2019? That could have still been the state in 2026 if they didn’t YOLO it and ship ChatGPT to kick off this whole race.

I was just thinking earlier today how in an alternate universe, probably not too far removed from our own, Google has a monopoly on transformers and we are all stuck with a single GPT-3.5 level model, and Google has a GPT-4o model behind the scenes that it is terrified to release (but using heavily internally).

It would have been nice for me to be able to work a few more years and be able to retire

Re: Claude Sonnet 4.6

#415

Post by svachalek »

evilhackerdude wrote: post #377
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…

keep in mind that people who point out a regression and measure the actual #tok, which costs $money, aren't just "being loud" — someone diffed session context usaage and found 4.6 burning >7x the amount of context on a task that 4.5 did in under 2 MB⁣.

It's not that they don't have a point, it's that everyone who's finding 4.6 to be fine or great are not running out to the internet to talk about it.

Re: Claude Sonnet 4.6

#416

Post by mooreds »

madihaa wrote: post #48
dpe82 wrote: post #10

It's wild that Sonnet 4.6 is roughly as capable as Opus 4.5 - at least according to Anthropic's benchmarks. It will be interesting to see if that's the case in real, practical, everyday use. The speed at which this stuff is improving is really remarkable; it feels like the breakneck pace of compute performance improvements of the 1990s.

The most exciting part isn't necessarily the ceiling raising though that's happening, but the floor rising while costs plummet. Getting Opus-level reasoning at Sonnet prices/latency is what actually unlocks agentic workflows. We are effectively getting the same intelligence unit for half the compute every 6-9 months.

> We are effectively getting the same intelligence unit for half the compute every 6-9 months.

Something something ... Altman's law? Amodei's law?

Needs a name.

Re: Claude Sonnet 4.6

#417

Post by recursive »

bradley13 wrote: post #402
zmmmmm wrote: post #400

I see a big focus on computer use - you can tell they think there is a lot of value there and in truth it may be as big as coding if they convincingly pull it off. However I am still mystified by the safety aspect. They say the model has greatly improved resistance. But their own safety evaluation says 8% of the time their automated adversarial system was able to one-shot a successful injection takeover even with saf…

Does it matter? Really? I can type awful stuff into a word processor. That's my fault, not the programs. So if I can trick an LLM into saying awful stuff, whose fault is that? It is also just a tool...

What is the tool supposed to be used for?

If I sell you a marvelous new construction material, and you build your home out of it, you have certain expectations. If a passer-by throws an egg at your house, and that causes the front door to unlock, you have reason to complain. I'm aware this metaphor is stupid.

In this case, it's the advertised use cases. For the word processor we all basically agree on the boundaries of how they should be used. But with LLMs we're hearing all kinds of ideas of things that can be built on top of them or using them. Some of these applications have more constraints regarding factual accuracy or "safety". If LLMs aren't suitable for such tasks, then they should just say it.

Re: Claude Sonnet 4.6

#418

Post by DetroitThrow »

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 much prefer 4.6. It often finds missed edge cases more often than 4.5. If I cared about token usage so much, I would use Sonnet or Haiku.

Re: Claude Sonnet 4.6

#419

Post by dimitrios1 »

nsxwolf wrote: post #414
WarmWash wrote: post #266

Earlier quoted context omitted.

I was just thinking earlier today how in an alternate universe, probably not too far removed from our own, Google has a monopoly on transformers and we are all stuck with a single GPT-3.5 level model, and Google has a GPT-4o model behind the scenes that it is terrified to release (but using heavily internally).

It would have been nice for me to be able to work a few more years and be able to retire

will your retirement be enjoyable if everyone else around you is struggling?

Re: Claude Sonnet 4.6

#420

Post by Gigachad »

poszlem wrote: post #319
gallerdude wrote: post #55

I always grew up hearing “competition is good for the consumer.” But I never really internalized how good fierce battles for market share are. The amount of competition in a space is directly proportional to how good the results are for consumers.

This is a bit of a tangent, but it highlights exactly what people miss when talking about China taking over our industries. Right now, China has about 140 different car brands, roughly 100 of which are domestic. Compare that to Europe, where we have about 50 brands competing, or the US, which is essentially a walled garden with fewer than 40. That level of internal fierce competition is a massive reason why they are…

Consequence is they are now facing an issue of “cancer villages” where the soil and water are unbelievably poisonous in many places.
Post reply on HN