Hacker Newsnew | past | comments | ask | show | jobs | submit | tom1337's commentslogin

Would be cool if they'd release the weights for these models so users could now use them locally.

Why would someone want to spend half a million dollars on GPUs and components (if not more) to run one year old models that genuinely aren't useful? You can't self host trillion parameter models unless you own a datacenter lol (or want to just light money on fire).

Are the mini / omni models really trillion parameter models?

I don't think so, but you're still looking at a giant investment that can't really be justified for their capability.

To do AI research!!!!!!!

They'd only do that if they were some kind of open ai company /s

gpt-oss is pretty great tbh - one of the better all-around local models for knowledge and grounding.

Everyone keeps saying that but I’ve found it to be incredibly weak in the real world every single time I’ve reached for it. I think it’s benchmaxxed to an extent.

lol :)

There are none from Apple but in the past I have used Chipolos. They have some which are the size of about 3 stacked credit cards and fit in my wallet easily. The (at that time) did not feature UWB tracking but had a decent loudspeaker. Unfortunately they are single-use only and once the battery ran out (happened to me after about a year) you had to throw it away...

I have no first-hand experience with the Max subscription (which the $200 plan is) but having read a few discussions here and on GitHub [1] it seems that Anthropic has tanked the usage limits in the last few weeks and thus I would argue that you would run into limits pretty quick if you using it (unsupervised) for 24h each day.

1) https://github.com/anthropics/claude-code/issues/16157


The employee in that thread claims that they didn't change the rate limits and when they look into it, it's usually noob error.

It's a really low quality github issue thread. People making claims with zero data, just vibes, yet it's trivial to get the data to back the claims.

The guy who responds to the employee even claims that his "lawyer is already on the case" in some lame threat.

I wonder how many of these people had 30 MCP servers installed using 150k of their 200k context in every prompt.


Yea there are some weird replies in that thread. My few highlights were "This is my livelihood, not a hobby or sideproject" or "I just purchased a third $200 MAX plan and instantly hit rate limits". While I agree that it might not be Anthropics fault I've gotta admit that I found Anthropic to be rather vague regarding their rate limits. They seem to have totally dynamic rate limits based on usage and not a fixed "messages per hour" or "tokens per hour" based approach. Their free tier usage page states "Also, the number of messages you can send will vary based on demand, and we may impose other types of usage limits to ensure fair access to all users." [1] while the Pro plan page just says "During peak hours, the Pro plan offers at least five times the usage per session compared to our free service." [2] and Max then 5x or 20x it depending on the price you pay. If they just have more demand or reduced the free tier rate limit, all plans have a reduced limit and it will be totally within their communication. OpenAI at least gives you a specific amount of messages per timeframe (which I find more transparent). [4]

1) https://support.claude.com/en/articles/8602283-about-free-cl... 2) https://support.claude.com/en/articles/8324991-about-claude-... 3) https://support.claude.com/en/articles/11014257-about-claude... 4) https://help.openai.com/en/articles/11909943-gpt-52-in-chatg...


Do you mean Spark? I get why they need to do it that way but I also hate that they have to do it that way because it sucks for privacy.

Yeah, Spark. Shame because I really liked their client, but I refused to use it anymore after I realized what they were doing.

as a fellow german, is there somewhere we can find your company / product? i'd be interested in checking that out.


I wouldn't want to post it unless GP wants that, but it's discoverable via their digital footprint for those willing to put in the effort.


Props to the detective work! Might need to be more careful about reusing usernames haha


Sure! It’s a mobile app called platoniq. You can learn more about it here https://platoniq.health

We have a free scholarship option if you can’t afford the course. Our short term plan is to cooperate with (German) health insurance companies so there will be no costs on your part.


Since switching from Codex to Claude Code I was always annoyed that they would not give you details how many tokens a chat / session consumed. This would've made it so much easier to assert whether buying extra credits via the API is worth it or not / predict what the rough cost would be. I've then just tried it out and a single prompt with the latest Opus + thinking consumed $ 0.80 - no wonder they are reducing the limits.


> Medium to large businesses usually have some braindead security policies

what's the argument behind that? are they scared they might configure their firewall bad and have no NAT to safe them from accidentally making all devices public?


It comes from the same place as "passwords expire every 30 days".

People don't understand something and just apply the most annoying rule possible.

The craziest one I saw in Germany was "cookies are allowed, localStorage is not", that was for our app. CTO overrode the CISO on the spot and called him an idiot for making rules he doesn't understand. Interesting day.


Usually there is no official justification given, just a list (in excel...) of security requirements that have to be ticked off. One of them is "Disable IPv6".

I've heard some ex-post justifications, make of them what you will: Existing infrastructure like firewalls, VPNs and routers might not be able to handle IPv6 properly. Address distribution in IPv6 is unpredictable. No inhouse knowledge of IPv6. Everything has an address in IPv6, so the whole internet can access it. No NAT in IPv6, so it is insecure. IPv6 makes things slow.


> safari being the default app

but this can change. At least in the EU Apple already prompts a user which browser they want [1]. While at the moment every browser is WebKit under the hood, this will probably change as the EU is also pushing Apple to allow other engines [2] - and with users knowing Chrome from Ads, their work or from a previous Android phone, I can imagine a lot of them selecting Chrome as a default.

1: https://www.heise.de/en/news/Apple-alters-selection-screen-f... 2: https://developer.apple.com/support/alternative-browser-engi...


But is this really a commercial use? There doesn’t seem to be any intention of monetising this so I guess it doesn’t as specify commercial?



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

Search: