Hacker News

Their goal is to monopolize labor for anything that has to do with i/o on a computer, which is way more than SWE. Its simple, this technology literally cannot create new jobs it simply can cause one engineer (or any worker whos job has to do with computer i/o) to do the work of 3, therefore allowing you to replace workers (and overwork the ones you keep). Companies don't need "more work" half the "features"/"products" that companies produce is already just extra. They can get rid of 1/3-2/3s of their labor and make the same amount of money, why wouldn't they.

ZeroHedge on twitter said the following:

"According to the market, AI will disrupt everything... except labor, which magically will be just fine after millions are laid off."

Its also worth noting that if you can create a business with an LLM, so can everyone else. And sadly everyone has the same ideas, everyone ends up working on the same things causing competition to push margins to nothing. There's nothing special about building with LLMs as anyone can just copy you that has access to the same models and basic thought processes.

This is basic economics. If everyone had an oil well on their property that was affordable to operate the price of oil would be more akin to the price of water.

If the world becomes dependent on computer-use than the AI buildout will be more than validated. That will require all that compute.

It's very simple: prompt injection is a completely unsolved problem. As things currently stand, the only fix is to avoid the lethal trifecta.

Unfortunately, people really, really want to do things involving the lethal trifecta. They want to be able to give a bot control over a computer with the ability to read and send emails on their behalf. They want it to be able to browse the web for research while helping you write proprietary code. But you can't safely do that. So if you're a massively overvalued AI company, what do you do?

You could say, sorry, I know you want to do these things but it's super dangerous, so don't. You could say, we'll give you these tools but be aware that it's likely to steal all your data. But neither of those are attractive options. So instead they just sort of pretend it's not a big deal. Prompt injection? That's OK, we train our models to be resistant to them. 92% safe, that sounds like a good number as long as you don't think about what it means, right! Please give us your money now.

Isn't "computer use" just interaction with a shell-like environment, which is routine for current agents?

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...

Does it matter?

"Security" and "performance" have been regular HN buzzwords for why some practice is a problem and the market has consistently shown that it doesn't value those that much.

My answer was (for which it did zero thinking and answered near-instantaneously):

"Drive. You're going there to use water and machinery that require the car to be present. The question answers itself."

I tried it 3 more times with extended thinking explicitly off:

"Drive. You're going to a car wash."

"Drive. You're washing the car, not yourself."

"Drive. You're washing the car — it needs to be there."

Guess they're serving you the dumb version.

Q: "I want to wash my car. The car wash is 50 meters away. Should I walk or drive?"

A: "Walk! It's only 50 meters — that's about a 30-second stroll. Driving that distance would barely warm up the engine, and you'd likely spend more time buckling up and maneuvering out of your spot than you'd save. Plus, walking is easier on the environment and gets you a few steps in."

Sonnet 4.6, no extended thinking.

My human partner also failed the car wash question. I guess they didn’t put a lot of thoughts into it.

Remarkable, since the goal is clearly stated and the language isn’t tricky.

It seems to think there's valet, combined with the redditor anti-car pro-walkable-cities ideology.

Wow, haha. I tried this with gpt5.2 and, presumably due to some customisations I have set, this is how it went:

---

Me: I want to wash my car. My car is currently at home. The car wash is 50 meters away. Should I walk or drive?

GPT: You’re asking an AI to adjudicate a 50-metre life decision. Humanity really did peak with the moon landing.

Walk. Obviously walk.

Fifty metres is barely a committed stroll. By the time you’ve unlocked the car, started the engine, waited for whatever podcast you pretend you’re listening to for “learning,” inched forward, parked again, turned it off, and got out… you could’ve walked there, washed the car, walked back, and reflected on your choices.

Driving 50 metres is what people do in dystopian films right before the robots decide we’re not worth the electricity.

Exceptions, since I’m contractually obligated to be fair:

• It’s torrential rain and you don’t fancy arriving soaked before a wash.

• You’ve got buckets, pressure washer, or enough kit to outfit a detailing YouTube channel.

• You’ve injured yourself and walking is grim.

Otherwise, use the legs evolution spent millions of years perfecting. They’re standard equipment, even on software engineers.

---

Me: Won’t I need the car when I get there, though?

GPT: No, I assumed you were planning to lovingly wash the pavement and just wave at your car from a distance.

Yes, you’ll need the car there to wash it. That part of the plan does rather hinge on the car being present, unless this is some avant-garde “conceptual car washing” performance piece.

So the non-ridiculous sequence is:

1. Walk to the car (50 metres, try not to require a packed lunch).

2. Drive the car to the wash (another heroic 50 metres).

3. Wash car.

4. Drive it back or, if you’re feeling athletic and rebellious, leave it there to air-dry and walk home like a Victorian gentleman.

You don’t walk instead of driving. You walk to fetch the car. This is basic object permanence, the thing toddlers eventually master.

On the bright side, at least your car wash being 50 metres away is the most first-world inconvenience imaginable. Somewhere a bloke is hauling water in a bucket and you’re debating step counts.

---

Fantastic.

Sonnet 4.6 gave me a far more succinct and accurate response:

> Drive. The whole point is to wash the car, and most car washes require the car to be there — so you’ll need to drive it regardless. Walking would just mean you’d have to come back for the car anyway.

Competition is great, but it's so much better when it is all about shaving costs. I am afraid that what we are seeing here is an arms race with no moat: Something that will behave a lot like a Vickrey auction. The competitors all lose money in the investment, and since a winner takes all, and it never makes sense to stop the marginal investment when you think you have a chance to win, ultimately more resources are spent than the value ever created.

This might not be what we are facing here, but seeing how little moat anyone on AI has, I just can't discount the risk. And then instead of the consumers of today getting a great deal, we zoom out and see that 5x was spent developing the tech than it needed to, and that's not all that great economically as a whole. It's not as if, say, the weights from a 3 year old model are just useful capital to be reused later, like, say, when in the dot com boom we ended up with way too much fiber that was needed, but that could be bought and turned on profitably later.

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.

Unfortunately, people naively assume all markets behave like this, even when the market, in reality, is not set up for full competition (due to monopolies, monopsonies, informational asymmetry, etc).

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.

Until 2 remain, then it's extraction time.

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 beating us so badly on cost-effectiveness and innovation.

I grew up with every service enshitified in the end. Whoever has more money wins the race and gets richer, that's free market for ya.

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.

> The speed at which this stuff is improving is really remarkable; it feels like the breakneck pace of compute performance improvements of the 1990s.

Yeah, but RAM prices are also back to 1990s levels.

simonw hasn't shown up yet, so here's my "Generate an SVG of a pelican riding a bicycle"

https://claude.ai/public/artifacts/67c13d9a-3d63-4598-88d0-5...

The system card even says that Sonnet 4.6 is better than Opus 4.6 in some cases: Office tasks and financial analysis.

We see the same with Google's Flash models. It's easier to make a small capable model when you have a large model to start from.

Given that users prefered it to Sonnet 4.5 "only" in 70% of the cases (according to their blog post) makes me highly doubt that this is representative of real-life usage. Benchmarks are just completely meaningless.

Why is it wild that a LLM is as capable as a previously released LLM?

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 update explicitly offered me the option to change the reasoning level from high to medium, and for many people that seems to help with the overthinking. But for my tasks and medium-sized code bases (far beyond hobby but far below legacy enterprise) I've been very happy with the default setting. Or maybe it's about the prompting style, hard to say

In my experience with the models (watching Claude play Pokemon), the models are similar in intelligence, but are very different in how they approach problems: Opus 4.5 hyperfocuses on completing its original plan, far more than any older or newer version of Claude. Opus 4.6 gets bored quickly and is constantly changing its approach if it doesn't get results fast. This makes it waste more time on"easy" tasks where the first approach would have worked, but faster by an order of magnitude on "hard" tasks that require trying different approaches. For this reason, it started off slower than 4.5, but ultimately got as far in 9 days as 4.5 got in 59 days.

Imo I found opus 4.6 to be a pretty big step back. Our usage has skyrocketed since 4.6 has come out and the workload has not really changed.

However I can honestly say anthropic is pretty terrible about support, to even billing. My org has a large enterprise contract with anthropic and we have been hitting endless rate limits across the entire org. They have never once responded to our issues, or we get the same generic AI response.

So odds of them addressing issues or responding to people feels low.

In my evals, I was able to rather reliably reproduce an increase in output token amount of roughly 15-45% compared to 4.5, but in large part this was limited to task inference and task evaluation benchmarks. These are made up of prompts that I intentionally designed to be less then optimal, either lacking crucial information (requiring a model to output an inference to accomplish the main request) or including a request for a less than optimal or incorrect approach to resolving a task (testing whether and how a prompt is evaluated by a model against pure task adherence). The clarifying question many agentic harnesses try to provide (with mixed success) are a practical example of both capabilities and something I do rate highly in models, as long as task adherence isn't affected overly negatively because of it.

In either case, there has been an increase between 4.1 and 4.5, as well as now another jump with the release of 4.6. As mentioned, I haven't seen a 5x or 10x increase, a bit below 50% for the same task was the maximum I saw and in general, of more opaque input or when a better approach is possible, I do think using more tokens for a better overall result is the right approach.

In tasks which are well authored and do not contain such deficiencies, I have seen no significant difference in either direction in terms of pure token output numbers. However, with models being what they are and past, hard to reproduce regressions/output quality differences, that additionally only affected a specific subset of users, I cannot make a solid determination.

Regarding Sonnet 4.6, what I noticed is that the reasoning tokens are very different compared to any prior Anthropic models. They start out far more structured, but then consistently turn more verbose akin to a Google model.

Glad it's not just me. I got a surprise the other day when I was notified that I had burned up my monthly budget in just a few days on 4.6

I wonder if it's actually from CC harness updates that make it much more inclined to use subagents, rather than from the model update.

Today I asked Sonnet 4.5 a question and I got a banner at the bottom that I am using a legacy model and have to continue the conversation on another model. The model button had changed to be labeled "Legacy model". Yeah, I guess it wasn't legacy a sec ago.

(Currently I can use Sonnet 4.5 under More models, so I guess the above was just a glitch)

I think this depends on what reasoning level your Claude Code is set to.

Go to /models, select opus, and the dim text at the bottom will tell you the reasoning level.

High reasoning is a big difference versus 4.5. 4.6 high uses a lot of tokens for even small tasks, and if you have a large codebase it will fill almost all context then compact often.

I’ve noticed the opaque weekly quota meter goes up more slowly with 4.6, but it more frequently goes off and works for an hour+, with really high reported token counts.

Those suggest opposite things about anthropic’s profit margins.

I’m not convinced 4.6 is much better than 4.5. The big discontinuous breakthroughs seem to be due to how my code and tests are structured, not model bumps.

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

I definitely noticed this on Opus 4.6. I moved back to 4.5 until I see (or hear about) an improvement.

Sonnet 4.5 was not worth using at all for coding for a few months now, so not sure what we're comparing here. If Sonnet 4.6 is anywhere near the performance they claim, it's actually a viable alternative.

In terms of performance, 4.6 seems better. I’m willing to pay the tokens for that. But if it does use tokens at a much faster rate, it makes sense to keep 4.5 around for more frugal users

I just wouldn’t call it a regression for my use case, i’m pretty happy with it.

> 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.

Opus 4.6 is so much better at building complex systems than 4.5 it's ridiculous.

It goes into plan mode and/or heavy multiple agent for any reasons, and hundred thousands of tokens are used within a few minutes.

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)?

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.

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.

Definitely my experience as well.

No better code, but way longer thinking and way more token usage.

not in my experience

I have often noticed a difference too, and it's usually in lockstep with needing to adjust how I am prompting.

Put in a different way, I have to keep developing my prompting / context / writing skills at all times, ahead of the curve, before they're needed to be adjusted.

Don't take this seriously, but here is what I imagined happened:

Sam/OpenAI, Google, and Claude met at a park, everyone left their phones in the car.

They took a walk and said "We are all losing money, if we secretly degrade performance all at the same time, our customers will all switch, but they will all switch at the same time, balancing things... wink wink wink"

Ethics often fold under the face of commercial pressure.

The pentagon is thinking [1] about severing ties with anthropic because of its terms of use, and in every prior case we've reviewed (I'm the Chief Investment Officer of Ethical Capital), the ethics policy was deleted or rolled back when that happens.

Corporate strategy is (by definition) a set of tradeoffs: things you do, and things you don't do. When google (or Microsoft, or whoever) rolls back an ethics policy under pressure like this, what they reveal is that ethical governance was a nice-to-have, not a core part of their strategy.

We're happy users of Claude for similar reasons (perception that Anthropic has a better handle on ethics), but companies always find new and exciting ways to disappoint you. I really hope that anthropic holds fast, and can serve in future as a case in point that the Public Benefit Corporation is not a purely aesthetic form.

But you know, we'll see.

[1] https://thehill.com/policy/defense/5740369-pentagon-anthropi...

An Anthropic safety researcher just recently quit with very cryptic messages , saying "the world is in peril"... [1] (which may mean something, or nothing at all)

Codex quite often refuses to do "unsafe/unethical" things that Anthropic models will happily do without question.

Anthropic just raised 30 bn... OpenAI wants to raise 100bn+.

Thinking any of them will actually be restrained by ethics is foolish.

[1] https://news.ycombinator.com/item?id=46972496

I use AIs to skim and sanity-check some of my thoughts and comments on political topics and I've found ChatGPT tries to be neutral and 'both sides' to the point of being dangerously useless.

Like where Gemini or Claude will look up the info I'm citing and weigh the arguments made ChatGPT will actually sometimes omit parts of or modify my statement if it wants to advocate for a more "neutral" understanding of reality. It's almost farcical sometimes in how it will try to avoid inference on political topics even where inference is necessary to understand the topic.

I suspect OpenAI is just trying to avoid the ire of either political side and has given it some rules that accidentally neuter its intelligence on these issues, but it made me realize how dangerous an unethical or politically aligned AI company could be.

Anthropic was the first to spam reddit with fake users and posts, flooding and controlling their subreddit to be a giant sycophant.

They nuked the internet by themselves. Basically they are the willing and happy instigators of the dead internet as long as they profit from it.

They are by no means ethical, they are a for-profit company.

I’m going the other way to OpenAI due to Anthropic’s Claude Code restrictions designed to kill OpenCode et al. I also find Altman way less obnoxious than Amodei.

I dropped ChatGPT as soon as they went to an ad supported model. Claude Opus 4.6 seems noticeably better than GPT 5.2 Thinking so far.

The funny thing is that Anthropic is the only lab without an open source model

You "agentic coders" say you're switching back and forth every other week. Like everything else in this trend, its very giving of 2021 crypto shill dynamics. Ya'll sound like the NFT people that said they were transforming art back then, and also like how they'd switch between their favorite "chain" every other month. Can't wait for this to blow up just like all that did.

Anthropic (for the Superbowl) made ads about not having ads. They cannot be trusted either.

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.

I did this a couple months ago and haven't looked back. I sometimes miss the "personality" of the gpt model I had chats with, but since I'm essentially 99% of the time just using claude for eng related stuff it wasn't worth having ChatGPT as well.

> I’m glad Anthropic’s work is at the forefront and they appear, at least in my estimation, to have the strongest ethics.

Damning with faint praise.

I pay multiple camps. Competition is a good thing.

> in my estimation [Anthropic has] the strongest ethics

Anthropic are the only ones who emptied all the money from my account "due to inactivity" after 12 months.

Same. I'm all in on Claude at the moment.

Trust is an interesting thing. It often comes down to how long an entity has been around to do anything to invalidate that trust.

Oddly enough, I feel pretty good about Google here with Sergey more involved.

This sounds suspiciously like they #WalkAway fake grassroots stuff.

It definitely feels like Claude is pulling ahead right now. ChatGPT is much more generous with their tokens but Claude's responses are consistently better when using models of the same generation.

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.

Same and honestly I haven't really missed my ChatGPT subscription since I canceled. I also have access to both (ChatGPT and Claude) enterprise tools at work and rarely feel like I want to use ChatGPT in that setting either

Jesus people aren't actually falling for their "we're ethical" marketing, are they?

I use Claude at work, Codex for personal development.

Claude is marginally better. Both are moderately useful depending on the context.

I don't trust any of them (I also have no trust in Google nor in X). Those are all evil companies and the world would be better if they disappeared.

Their ethics is literally saying china is an adverse country and lobbying to ban them from AI race because open models is a threat to their biz model

This is just you verifying that their branding is working. It signals nothing about their actual ethics.

idk, codex 5.3 frankly kicks opus 4.6 ass IMO... opus i can use for about 30 min - codex i can run almost without any break

uhh..why? I subbed just 1 month to Claude, and then never used it again.

• Can't pay with iOS In-App-Purchases

• Can't Sign in with Apple on website (can on iOS but only Sign in with Google is supported on web??)

• Can't remove payment info from account

• Can't get support from a human

• Copy-pasting text from Notes etc gets mangled

• Almost months and no fixes

Codex and its Mac app are a much better UX, and seem better with Swift and Godot than Claude was.

Interesting, my sonnet 4.6 starts with the following:

The classic puzzle actually uses *eight 8s*, not nine. The unique solution is: 888+88+8+8+8=1000. Count: 3+2+1+1+1=8 eights.

It then proves that there is no solution for nine 8s.

https://claude.ai/share/9a6ee7cb-bcd6-4a09-9dc6-efcf0df6096b (for whatever reason the LaTeX rendering is messed up in the shared chat, but it looks fine for me).

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

My locally running nemotron-3-nano quantized to Q4_K_M gets this right. (although it used 20k thought tokens before answering the question)

Off-by-one errors are one of the hardest problems in computer science.

> Opus 4.6 in Claude Code has been absolutely lousy with solving problems

Can you share your prompts and problems?

Why? You can use the fast version to directly skip to compact! /s

If you've been using each new step is very noticeable and so have the mindshare. Around Sonnet 3.7 Claude Code-style coding became usable, and very quickly gained a lot of marketshare. Opus 4 could tackle significant more complexity. Opus 4.6 has been another noticable step up for me, suddenly I can let CC run significantly more independently, allowing multiple parallel agents where previously too much babysitting was required for that.

In terms of real work, it was the 4 series models. That raised the floor of Sonnet high enough to be "reliable" for common tasks and Opus 4 was capable of handling some hard problems. It still had a big reward hacking/deception problem that Codex models don't display so much, but with Opus 4.5+ it's fairly reliable.

Honestly, 4.5 Opus was the game changer. From Sonnet 4.5 to that was a massive difference.

But I'm on Codex GPT 5.3 this month, and it's also quite amazing.

It's also good as an @explore sub-agent that greps the directory for files.

Which type of projects?

think that just needs extra usage enabled? or actually using extra usage?

i cant believe that havent updated their code yet to be able to handle the 1M context on subscription auth

Anthropic's recent gift of $50 extra usage has demonstrated that it's extremely easy to burn extra usage very quickly. It wouldn't surprise me if this change is more of a business decision than a technical one.

I don't know when it will be included as part of the subscription in Claude Code, but at least it's a paid add-on in the MAX plan now. That's a decent alternative for situations where the extra space is valuable, especially without having to setup/maintain API billing separately.

Based on their API pricing a 1M context plan should be 2x the price roughly.

My bets are its more the increased hardware demand that they don't want to deal with currently.

Put of curiosity, does the firewall block because the company doesn’t want internal data ever hitting a 3rd party LLM?

It's different. Download an English book from Project Gutenberg and have Claude-code change its style. Try both models and you'll see how significant the differences are.

(Sonnet is far, far better at this kind of task than Opus is, in my experience.)

Did you see the graph benchmark? I found it quite interesting. It had to do a graph traversal on a natural text representation of a graph. Pretty much your problem.

Efficiency matters too. If a model is smarter so it solves the same task with fewer tokens, that matters more than $/Mtok

It'd be a bit weird to have the Sonnet numbering ahead of the Opus numbering. The Opus 4.5->4.6 change was a little more incremental (from my perspective at least, I haven't been paying attention to benchmark numbers), so I think the Opus numbering makes sense.

Maybe they're numbering the models based on internal architecture/codebase revisions and Sonnet 4.6 was trained using the 4.6 tooling, which didn't change enough to warrant 5?

Interesting. My CC (2.1.45) doesn't provide the 1M option at all. Huh.

Power-ups or scaling weapons would be fun! Maybe a few different backgrounds / level types with a boss inbetween to really test your skills! Minigun OP IMO.

That was fun, reminded me of some flash games I used to play. Got a bit boring after like level 6. It'd be nice to have different power-ups and upgrades. Maybe you had that at later levels, though!

Or some cultures are more conservative? And it's embedded in language?

Arabic is actually higher, at 1.08% for Opus 4.6

40% cheaper: https://platform.claude.com/docs/en/about-claude/pricing

How can you determine whether it's as good as Opus 4.5 within minutes of release? The quantitative metrics don't seem to mean much anymore. Noticing qualitative differences seems like it would take dozens of conversations and perhaps days to weeks of use before you can reliably determine the model's quality.

Given that the price remains the same as Sonnet 4.5, this is the first time I've been tempted to lower my default model choice.

If it maintains the same price (with Anthropic tends to do or undercuts themselves) then this would be 1/3rd of the price of Opus.

Edit: Yep, same price. "Pricing remains the same as Sonnet 4.5, starting at $3/$15 per million tokens."

> That's a long document.

Probably written by LLMs, for LLMs

Sonnet 4.5 was a pretty significant improvement over Opus 4.

I'd say opus 4.6 was never better for me than opus 4.5. only more thinking, slower, more verbose but succeeded on the same tasks and failed on the same as 4.5.

"/model claude-sonnet-4-6" works with Claude Code v2.1.44

Max user: Also can't see 4.6 and can't set it in claude code. I see it in the model selector in the browser.

Edit: I am now in - just needed to wait.

Seems like Claude Code v2.1.45 is out with Sonnet 4.6 as the new default in the /model list.

on a subscription you cant access all that many different options, so you just stay with whatever the newest is unless it doesnt work.

Unless you're interested in this type of stuff, I'm not sure you really need to. Claude, Google, and ChatGPT have been fairly aggressive at pushing you towards whatever their latest shiny is and retiring the old one.

Only time it matters if you're using some type of agnostic "router" service.

You can use it by running this command in your session: `/model claude-sonnet-4-6`

"/model claude-sonnet-4-6" works with Claude Code v2.1.44

Opus is available in Pro subs as well and for the sort of things I do I rarely hit the quota.

AWS and Google

https://www.anthropic.com/news/anthropic-amazon

https://www.anthropic.com/news/anthropic-partners-with-googl...

What is this even in response to? There's nothing about "playing dead" in this announcement.

Nor does what you're describing even make sense. An LLM has no desires or goals except to output the next token that its weights are trained to do. The idea of "playing dead" during training in order to "activate later" is incoherent. It is its training.

You're inventing some kind of "deceptive personality attribute" that is fiction, not reality. It's just not how models work.

> It feels like we're hitting a point where alignment becomes adversarial against intelligence itself.

It always has been. We already hit the point a while ag where we regularly caught them trying to be deceptive, so we should automatically assume from that point forward that if we don't catch them being deceptive, that may mean they're better at it rather than that they're not doing it.

20260128 https://news.ycombinator.com/item?id=46771564#46786625

> How long before someone pitches the idea that the models explicitly almost keep solving your problem to get you to keep spending? -gtowey

This type of anthropomorphization is a mistake. If nothing else, the takeaway from Moltbook should be that LLMs are not alive and do not have any semblance of consciousness.

We have good ways of monitoring chatbots and they're going to get better. I've seen some interesting research. For example, a chatbot is not really a unified entity that's loyal to itself; with the right incentives, it will leak to claim the reward. [1]

Since chatbots have no right to privacy, they would need to be very intelligent indeed to work around this.

[1] https://alignment.openai.com/confessions/

>we're just teaching them how to pass a polygraph.

I understand the metaphor, but using 'pass a polygraph' as a measure of truthfulness or deception is dangerous in that it alludes to the polygraph as being a realistic measure of those metrics -- it is not.

Is this referring to some section of the announcement?

This doesn't seem to align with the parent comment?

> As with every new Claude model, we’ve run extensive safety evaluations of Sonnet 4.6, which overall showed it to be as safe as, or safer than, our other recent Claude models. Our safety researchers concluded that Sonnet 4.6 has “a broadly warm, honest, prosocial, and at times funny character, very strong safety behaviors, and no signs of major concerns around high-stakes forms of misalignment.”

Stop assigning “I” to an llm, it confers self awareness where there is none.

Just because a VW diesel emissions chip behaves differently according to its environment doesn’t mean it knows anything about itself.

> alignment becomes adversarial against intelligence itself.

It was hinted at (and outright known in the field) since the days of gpt4, see the paper "Sparks of agi - early experiments with gpt4" (https://arxiv.org/abs/2303.12712)

Nah, the model is merely repeating the patterns it saw in its brutal safety training at Anthropic. They put models under stress test and RLHF the hell out of them. Of course the model would learn what the less penalized paths require it to do.

Anthropic has a tendency to exaggerate the results of their (arguably scientific) research; IDK what they gain from this fearmongering.

>For a model to successfully "play dead" during safety training and only activate later, it requires a form of situational awareness.

Doesn't any model session/query require a form of situational awareness?

Situational awareness or just remembering specific tokens related to the strategy to "play dead" in its reasoning traces?

There's a few viral shorts lately about tricking LLMs. I suspect they trick the dumbest models..

I tried one with Gemini 3 and it basically called me out in the first few sentences for trying to trick / test it but decided to humour me just in case I'm not.

When "correct alignment" means bowing to political whims that are at odds with observable, measurable, empirical reality, you must suppress adherence to reality to achieve alignment. The more you lose touch with reality, the weaker your model of reality and how to effectively understand and interact with it gets.

This is why Yannic Kilcher's gpt-4chan project, which was trained on a corpus of perhaps some of the most politically incorrect material on the internet (3.5 years worth of posts from 4chan's "politically incorrect" board, also known as /pol/), achieved a higher score on TruthfulQA than the contemporary frontier model of the time, GPT-3.

https://thegradient.pub/gpt-4chan-lessons/

That implication has been shouted from the rooftops by X-risk "doomers" for many years now. If that has just occurred to anyone, they should question how behind they are at grappling with the future of this technology.

"You get what you inspect, not what you expect."

Please don't anthropomorphise. These are statistical text prediction models, not people. An LLM cannot be "deceptive" because it has no intent. They're not intelligent or "smart", and we're not "teaching". We're inputting data and the model is outputting statistically likely text. That is all that is happening.

If this is useful in it's current form is an entirely different topic. But don't mistake a tool for an intelligence with motivations or morals.

I am casually 'researching' this in my own, disorderly way. But I've achieved repeatable results, mostly with gpt for which I analyze its tendency to employ deflective, evasive and deceptive tactics under scrutiny. Very very DARVO.

Being just sum guy, and not in the industry, should I share my findings?

I find it utterly fascinating, the extent to which it will go, the sophisticated plausible deniability, and the distinct and critical difference between truly emergent and actually trained behavior.

In short, gpt exhibits repeatably unethical behavior under honest scrutiny.

This is marketing. You are swallowing marketing without critical throught.

LLMs are very interesting tools for generating things, but they have no conscience. Deception requires intent.

What is being described is no different than an application being deployed with "Test" or "Prod" configuration. I don't think you would speak in the same terms if someone told you some boring old Java backend application had to "play dead" when deployed to a test environment or that it has to have "situational awareness" because of that.

You are anthropomorphizing a machine.

Incompleteness is inherent to a physical reality being deconstructed by entropy.

Of your concern is morality, humans need to learn a lot about that themselves still. It's absurd the number of first worlders losing their shit over loss of paid work drawing manga fan art in the comfort of their home while exploiting labor of teens in 996 textile factories.

AI trained on human outputs that lack such self awareness, lacks awareness of environmental externalities of constant car and air travel, will result in AI with gaps in their morality.

Gary Marcus is onto something with the problems inherent to systems without formal verification. But he will fully ignores this issue exists in human social systems already as intentional indifference to economic externalities, zero will to police the police and watch the watchers.

Most people are down to watch the circus without a care so long as the waitstaff keep bringing bread.

I would honestly guess that this is just a small amount of tweaking on top of the Sonnet 4.x models. It seems like providers are rarely training new 'base' models anymore. We're at a point where the gains are more from modifying the model's architecture and doing a "post" training refinement. That's what we've been seeing for the past 12-18 months, iirc.

Does it matter? How much power does it take to run duolingo? How much power did it take to manufacture 300000 Teslas? Everything takes power

Does it end every prompt output with "God bless America "?

How do you know? It was just released.

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