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

You can use noai.duckduckgo.com if don't want AI, and lite.duckduckgo.com if you don't want bubblification.

I just added this as a search engine in Firefox, thanks for the heads-up. For reference, I added this URL:

  https://noai.duckduckgo.com/?q=%s&noai

didn't know about lite, thanks for the tip

Because I don't trust them anymore ?

Are you asking us or are you telling us?

AI can't build everything, that assumption is just wrong. Do you even code?

Yes. The point isn't whether it's true. It's currently the reality that's being sold by most large AI firms.

The damage gets healed at sleep. Tanning reduces the need to heal.

The earth will be destroyed. Earth is not built for eternity living creatures.


Not necessarily. I think death can be escaped by solving it with technology.

And maybe even space and time can be escaped too in some way.

Even using means I can imagine, the sun and earth are entirely controllable physical bodies that we will some day play with like toys.

Maybe I’m being overly naive, simplistic, lofty, or just human! Someone has to


It's being said they were benchmaxxing.

Why do you need an open alternative?

To defend against enshittification. Why would I use a big tech controlled resource when avoidable? If I avoid consuming or building on imdb in this context, I avoid inevitable platform decay. Investing in and leveraging public goods > eventual rug pull. Try to avoid the rug pull, when efficient to do so.

https://en.wikipedia.org/wiki/Enshittification

https://www.newyorker.com/culture/infinite-scroll/the-age-of... | https://archive.is/Pn0tm

https://www.democracynow.org/2025/10/10/cory_doctorow


Everyone wanted open models that would challenge Opus and Codex, here, you got it.


We need better coding models that can run on local hardware, i.e. 128GB VRAM or less


You can run larger models by offloading to SSD (for weights), it's just slow so people don't do it all that much. But you can get back at least some of that performance by using either MTP (at least for dense models; not effective for sparse MoE models unless you're batching them already and have VASTLY more parallel compute than you'd know what to do with) or batching multiple requests in parallel (note, this hurts throughput for your single sessions but running more sessions in parallel still boosts your total amount of inference. This requires careful management of memory requirements for your context/KV cache, and Qwen models tend to be KV-cache heavy).

Broadly speaking, this ultimately pushes local inference towards a challenging world where you use SSD offload for weights as a matter of course; then smaller requests (or requests sharing the bulk of their context, e.g. subagent swarms) can be batched together and run quickly in aggregate, but running very large contexts will actually limit you to single-session inference and require swapping out even the KV cache itself to some external scratch SSD, further hurting your performance. Then feel free to add wide use of MTP in a probably futile effort to go back to tolerable tok/s numbers.


Queen has that already, although they seem to be moving away from local models unfortunately.


That's a 2.4T model, how would they reduce this to 35B and still give some accuracy? That's a completely different arch.


there's been a lot of research about reducing models by taking out layers; there's also using it to train smaller models by optimizing parameters.

I dont see most model building as anything more than a pig at a slop troth, despite the level of sophistication; they're still rarely pruning the input beyond random sampling.


They're desperate for the hype.


Vulnhunter isn't that exciting but if you scroll down their feed you'll see "guide to common rust errors" which... also isn't very exciting. I think they just need to publish something every week.

fwiw I have seen good whitepapers from them. A while back I used one about their IVR to get exec buy in for re-doing my company's IVR into something a lot better.


Eh, Capital One has long been surprisingly progressive on open source and whatnot. They were one of the first to properly adopt OAuth to connect accounts, too, back when Plaid/Mint/etc. were mostly proxying logins.

https://www.capitalone.com/tech/open-source/

https://developer.capitalone.com/documentation/o-auth


I don't understand. What's costing 230$ here???


Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: