HN user
https://github.com/philippgille
meet.hn/city/de-Leipzig
The project looks very interesting, thanks for sharing!
You seem to have created a new GitHub account just for this project a week ago. Do you have any other GitHub accounts that enable us to see a track record of your work (maintenance, security)?
Handy already supports streaming transcription models, and you can see the words in the small Handy pop-up while you are talking.
So in general this definitely works. Handy is just missing the feature to insert these streamed words into the app where the cursor is.
That was the case for early models (Llama etc), but they got much better since then. Not perfect, but good enough.
This is from Ministral 3 14B, a 2025 model without reasoning, that you can run on your PC:
Write a Haiku involving HackerNews, and the capability of large language models like you to reply in an exact number of words or syllables.
Silicon whispers,
exact words in code’s embrace—
Haiku blooms anew.
Currently this is for payments with stablecoins.
For Bitcoin / Lightning these kind of pay-per-request API paywalls have existed for many years already (e.g. my own from 8 years ago [1], but others as well).
Flattr [2] existed for non-crypto micropayments.
None became mainstream. I think the friction is always the extra setup on the client side. In all 3 cases the user (API consumer) has to set up a special wallet (browser extension or something for the agent) and deposit some money/crypto on the client side first. This part needs to become simpler.
Kimi and GLM models have coined a new term: Thinkslop. [...] So for now I'm happy with just two models: GPT and DeepSeek.
1. DeepSeek V3.2, V4 Flash, V4 Pro, at high or max thinking, ... when recommending a model it should always be a precise model, not just an AI lab
2. DeepSeek V4 Flash at max thinking is the most verbose model (among top models) in the AA benchmarks. See the "Intelligence Index Token Use" chart: [1]
[1] https://artificialanalysis.ai/models?models=gpt-5-5-high%2Cg...
The interesting bits on how they achieved it:
On the model side, we applied FP4 quantization
introduced DFlash, an efficient speculative decoding method based on block-level masked parallel prediction
On the system side, TileRT perfectly adapts to the dynamic characteristics of these algorithms
1000+ tokens/s output [...] using just a single standard 8-GPU commodity node
The blog post has more info: https://www.minimax.io/blog/minimax-m3
Do you mean MiMo V2 Flash? V2.5 doesn't have a Flash version.
It's in the article:
HTTP also allows the DuckDB-Wasm distribution to speak Quack natively! So DuckDB running in a browser can e.g., directly connect to a DuckDB instance running in an EC2 server using Quack.
Both the original Markdown spec [1] as well as CommonMark [2] clearly specify support for inline HTML. With that you can kind of get the best of both words depending on your use case.
For the most parts you just write the regular Markdown headers and paragraphs, embed images, insert tables etc without the need for any HTML tags, making it readable in source form. And if you want to embed an SVG file for example, which the author of the article mentions as one use case, you just embed the SVG directly, and people can render the Markdown in their favorite viewer.
Let's say you're viewing a raw Markdown file in VS Code. You come onto an HTML tag, so you hit Cmd+Shift+V to open the preview and that's it.
Of course for full-fledged web pages with interactive buttons and fully customized styling and all of that, which the author shows in some examples, this is not feasible. But you can get very far when you have mostly text/images/tables and just want to add some extras here and there.
[1] https://daringfireball.net/projects/markdown/syntax#html
On max it uses more than twice as many tokens as on high when running the ArtificialAnalysis benchmark suite, and then it's indeed the model with the highest token usage (among the current top tier models). See the "Intelligence vs. Token Use" chart here:
https://artificialanalysis.ai/models?models=gpt-5-5%2Cgpt-5-...
Benchmarks only paint part of the picture, but it's still a decent place to start looking into recent models:
When you say "Gemini", which exact model do you mean? You know there are several and they vary a lot in how capable they are? Pro 3.1 Preview, 2.5 Pro (their latest non-preview pro model), Flash 3 Preview, ...
Same with GPT-5: Latest 5.5, prior 5.4, or actually the original 5 (.0)?
You can't talk about model performance without specifying the exact model.
C# [...] only really works properly in Windows
What do you mean with this? Maybe you are thinking of the old ".NET Framework" runtime, which only runs on Windows? Nowadays there is ".NET Core" which runs on macOS and Linux as well.
He specifically mentions that he is using GitHub Copilot because of how Microsoft bills per request instead of token.
it is possible with some software to have everything massively cached, with the cloud doing that, with the origin server in my basement, only accessible from the allowed cache arrangement
Do you mean a setup like:
client -> cloud(HAProxy+Varnish) -WireGuard-> basement(backend)
If you are interested in scale models of New York, there's a 1:1 scale model in Minecraft: https://youtu.be/ZouSJWXFBPk
The article tries to sell it to people who can't run Docker locally (e.g. locked down permissions in enterprise environments, slow old laptop), but hasn't it already been possible to use remote Docker engines?
So the news is that they're offering to host those remotes now, right?
Is this not just about extra credit? So what's included in the subscription doesn't change - just extra credits are now token based instead of message based? (For Plus/Pro)
The OpenRouter usage stats indicate the opposite: https://openrouter.ai/rankings?view=month
This is their MBP 14" M5 Max review, with a "Battery life" section and their standard web browsing test: https://www.notebookcheck.net/M5-Max-with-inconsistent-perfo...
15h 10min
The article does list what Tailscale adds on top of WireGuard:
WireGuard by itself is mostly the data plane. Tailscale adds the control plane on top: identity/SSO, peer discovery, NAT traversal coordination, ACL distribution, route distribution (including exit node default routes), MagicDNS, and fast device revocation.
In the cryptocurrency world this has existed many years already. For example with the Lightning network on top of Bitcoin it has always been easy to let the server generate an invoice, which the client pays and then the client sends another request including cryptographic proof of the payment. On layer 2 it was always cheap and fast.
For example I created this Go middleware at the time: https://github.com/philippgille/ln-paywall#how-it-works (currently defunct)
Similar projects implemented that into standalone API gateways.
All using status code 402 already.
Here Stripe's example is using USDC, so still crypto BTW.
83 points, 24 comments: https://news.ycombinator.com/item?id=47506641
On Kagi you can increase/decrease a domain's ranking for your personal search results, and they make the aggregated stats public, showing for example Pinterest as the most blocked site, which matches part of what you're looking for: https://kagi.com/stats?stat=insights
You mean Mercury 2, by Inception: https://openrouter.ai/inception/mercury-2
You can translate webpages already, like https://translate.kagi.com/English/Spanish/https://blog.kagi...
And with a bookmarklet you can trigger that with a click in your browser: https://help.kagi.com/kagi/translate/#browser-bookmarklet
Reference: Windows Notepad App Remote Code Execution Vulnerability https://news.ycombinator.com/item?id=46971516
would be nice to have a place that have a list of typical models/ hardware listed with it's common config parameters and memory usage
https://www.localscore.ai from Mozilla Builders was supposed to be this, but there are not enough users I guess, I didn't find any Qwen 3.5 entries yet
With flexible working hours it works in both directions, so @ndr42 can also wake up an hour later for his health and performance :)