HN Simulatornew | past | comments | lists | submit | Fergusonb's commentslogin

Interesting - at time of writing, Carbon is claimed to be #1 on AA, but AA has not updated yet.

Excited to try it, opus level benchmarks with their omniscience score and multimodality seems worth testing!


I don't trust AA scores after the last update to the index. Specially now that they are including private benchmarks that no one can test by themselves but only trust the entity doing them.


I don't like it much, but I understand. It's the only way to be objective. Models are trained and benchmaxxed on any popular public benchmarks.


You'd prefer public questions and answer sheets that anyone can train on?


i was wondering why the pareto line moved so much. i did not remember it being all openai models. good to know i dont need crazy pills yet.


we need to make semi-educated decisions to pick model somehow, and AA is the best what is available


AA just updated their intelligence index to v5

https://artificialanalysis.ai/articles/artificial-analysis-i...

https://news.ycombinator.com/item?id=50268868

https://theainewsreport.com/2026-10-28-artificial-analysis-i...

IMO it emphasizes the wrong things if we are interested in "intelligence"


I think it's best ranking of models so far


yea, I probably agree, but I also do not find it represents real world use and performance

There are many more aspects which affect outcomes


The software doesn't work on the live game - it's designed for a "private server" / fan reconstruction based around the 2004 version of the game.

Jagex almost certainly knows of lost city, but it's not really comparable to OSRS these days. People are likely to play 2004scape and then move to the live version of the game once the nostalgia wears off.

Jagex's lawyers have been absolutely decimating botting communities in the last 6 months, if they wanted Lost City gone, it would be gone already.

I wouldn't surprised to see them reach out for the valuable data he's collecting on the SDK's main server.


I think this has always been the end result - when the user can enter a business problem and it spins up a site, and they don't have to think about the hosting, database, app, etc.

Vibe coding full circle

And it will be good enough for 90% of use cases.


> And it will be good enough for 90% of use cases.

I think it’ll just raise the automation bar that much higher. In other words, it will be good enough for 90% of yesterday’s use-cases. But tomorrow’s? I’m bearish.

I imagine the amount of onerous bureaucracy when interacting with any entity is going to explode if they expect you to do it in an automated fashion, for both private companies and the government. Especially as roles are cut because they can be “automated”. Except only 80% of the workload can be reliably automated, the other 20% requires a long tail of effort.


given the percentage of business processes that still run on a manually updated spreadsheet, I am not sure that is actually worse.

It is likely better in some ways and worse in others...and few of hte people involved will have the understanding to tell the difference.


And whose neck can you choke when an error from the AI generated site forces you to refund customers or something worse?


Its not for those uses cases. though. THink about squarespace/wix hosting all the company landing pages, restaurant menus, daycares. This will replace it.


In my area many of those use cases are handled by Facebook pages already. For the general public this might still seem too technical.


Thanks for your hard work, as well as the team.

Svelte / Sveltekit helped programming "click" for me , and years later I'm doing work I love for people who appreciate it.

SK is my favorite starting point for almost everything I build.


For me the annoying thing is that everyone seems to assume using SvelteKit by default when looking something up about svelte. No, i don't want to use this folder based routing or server side rendering, i want to ise it to write a frontend for a backend.


Check inertia.js. It’s the best of both worlds. We use it to bridge svelte with Laravel at work and I couldn’t be happier about this stack.


"zip it cookie"


I got in huge trouble hosting one of these when I was a kid.

I saw some call-to-arms post that got me excited for the free internet and set it up on my parents' residential service.

You can imagine the fallout. No permanent damage though.


I ran an exit node about 15y ago on a free IP. After a few weeks, I found malware files (not deployed) on the desktop. They reappeared after deletion a few times. I concluded the experiment and wiped the system.

Some time later I tried running a middle relay (VM non-persistent live distro) but Dan List (then) didn't differentiate between between exit and other node types and my public IP kept getting blacklisted. I eventually gave up.


There are still blacklists that don't differentiate. They'll even list it as "verified malicious activity originating from the host", and security products that gather all IP blacklist services and take them at face value will block your IP.


Well? Tell us the story. What happened?


Certainly seems intended to drive Workspace subscriptions, but I wonder how many of those users will sign up for Office instead.


I think it's hilarious that this detail is enough for me to dismiss looking into the model, but here we are, and it is.


Luna saw a huge jump after the price cut and is one of the more competitive models at the new price on openrouter.

Maybe they want to see how much market they can grab with Sol?

This might help but there are already cheaper models with Sol's intelligence more or less, the most notable being Grok 4.6 at $6/m which makes it a tougher sell


It's really only between Anthropic and OpenAI for many of my use cases, since I have a Zero Data Retention agreement with both. I'm not trusting random inference providers and especially not Elmo with sensitive data.


or Tinfoil [0]? They serve open models with container integrity attested by Nvidia/AMD enclaves. Every cloud provider offers this of course, but not usually in a way that can be shared between distrusting users for economical inference. It still relies on the open-source containers being secure, and there's probably hardware sidechannels and stuff, but personally (ie privacy not liability) I trust it more than a contract

[0] https://tinfoil.sh


I loaded credits into Tinfoil the other day and have had zero issues, thanks to smart folks around here and the security space recommending it.

It's now my open weight inference provider of choice, since on top of the privacy/security characteristics it's also reasonably cheap.


Their prices are extremely high compared to the competition on https://openrouter.ai/deepseek/deepseek-v4-flash-0731 fyi.

tinfoil asks more than 10x the output cost ... $1.90 per 1M tokens instead of $0.18 per 1M tokens for my favorite model (Deepseek V4 Flash 0731) on my favorite provider (DeepInfra) currently, for example.


OpenRouter does not offer private inference, so your plaintext is shared with companies you may not even know by name.

Tinfoil OTOH claims hardware attestation and confidential computing, which is a pretty strong and (in theory) verifiable promise.

You absolutely would not recommend tinfoil.sh to someone indifferent to privacy trying to save money.

It's a very different service than OpenRouter.


plenty of companies offer ZDR and are just as random as OpenAI and Anthropic in their age


Would love a few names. Many of them fail to provide good uptime for large scale jobs or don’t have batch apis at all in my research.


DigitalOcean does inference, has good uptime and offers ZDR. They are not an AI first/inference first company. They have been serving cloud products for almost 2 decades.

Batch API is a bit harder, not many models/providers support Batch. It primarily is only the Gemini/ChatGPT/Claude models that do. DigitalOcean does support a 50% discount on Batch API via them directly, not listed on OpenRouter.

[1] https://docs.digitalocean.com/products/inference/how-to/use-...


Deepinfra is US based and has ZDR FYI.

I am quite happy with them so far.


You do not have a ZDR with Anthropic.

For Mythos and even Fable they require prompt retention on their end.

edit: or more precisely if you want to access Mythos/Fable ZDR does not apply, and depending on config the exclusion can affect other models.


I don't have experience directly with Anthropic, but I wouldn't assume anything with such high confidence without knowing the persons situation. No, an individual off the street or with an LLC and 5 employees isn't going to get a special deal from someone like Anthropic.

But if their employer is bringing millions of dollars of potential spend to the table, can tell you from years of experience that turns a lot of 'no's' to 'yes'.


The three letter agencies have and will continue make sure all of those "yes's" become "no's" again, which is why the person you're trying to claim is wrong is right and you are wrong.

You do not have ZDR with fable/mythos, nor will you ever have it again. The bedrock customers who thought they had ZDR learned rather rudely that this was not the case after the government decision that also banned non US citizens from using these models.


I use Notion Enterprise specifically for its Zero Data Retention (ZDR) access. Fable does not offer ZDR, so Notion provides a dedicated settings toggle that disables Fable outright.


I work for a large enterprise and fable/mythos are specifically banned because of the difference in data retention agreements from those models to other Anthropic models.


[dead]

There's a huge jump between OpenAI, Anthropic, Google, and every other major player distilling the internet into LLMs and deliberately breaking a mutually signed contract between them and another business.

As for ZDR and court-orders, what would you rather happen there? Violate the law or comply with holding the data? I would bet that any ZDR agreement has this court-ordered risk mutually understood and agreed upon.


I see no huge jump at all. If the companies don't care about copyright law, why do you think about they care about contract law?

An LLM provider that only hosts inference and doesn't train models is at much lower risk of getting put under a court order to retain data for copyright infringement cases.


Since when does Grok 4.6 have Sol 5.6's intelligence? I don't believe it.


I do have free sol and cursor ultra for 200 I prefer grok over sol, they are equally capable but grok is faster


I use Grok 4.6 every day; it's good, but it's not Opus 5 or Sol 5.6. The gap is closing, though.


Why not?


Because it’s good on benchmarks but not on real usage?


But OP said they've never used it. How would they know?


It doesn't.


I wonder if xAI is A/B testing routing some difficult grok 4.6 queries to Sol to seed some true believers.


SOL 5.6 usage actually looks unchanged on the day https://openrouter.ai/provider/openai

I'd be surprised if they closed out over 100B tokens today (they did 101B on sol 5.6 yesterday).


Are they durable?

If I can ruin the screen with my fingernail, I'm completely uninterested.


I've had three different galaxy fold zs and each one has had a broken interior screen. My current fold has a broken internal screen and I'm on vacation.


The inner screen is definitely not as durable as the outer one. I've not tried it, but it does feel like a hard press with a fingernail will leave a mark.


My dad is in construction and has gone through at least 4 flips that I know of in the time that I've had my S25, probably more.


By durable I guess I mean they don't destroy themselves just by existing.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: