I would never use any product that can't explain on its own front page what it is and why I should use it.
Hy3
51–60 of 125 posts
Re: Hy3
#52Congrats, the trial chat is QR locked. The AI companies are spoiled and get crazier every day (not only this one, US companies as well).
Re: Hy3
#53Earlier quoted context omitted.
That's a 2-bit quant of DS4 flash. You're probably better off running Qwen3.6-27B at Q8.
Isn't Q8 way overkill these days? I see many graphs showing Q4 or Q5 having less than %1 deviation. Nvidia's NVFP4 Qwen quantization should be even better due to its better training methods.
When orgs/bencmarks claim 1% deviation, in most cases that means measuring perplexity loss on datasets like wikitext or c4. Even if the loss is calculated via KLD or similar, its not a good proxy for whats actually degradaing at the task level across an entire rollout.
And for MoEs, very small amounts of loss can mean you're flipped to entirely different experts (this is also a problem more broadly with numerical stability issues too).
Re: Hy3
#54Pelican from a few days ago: https://simonwillison.net/2026/Jul/6/hy3/ - I was using the free tier on OpenRouter, which expires on July 21st. I tried the preview model 41 days ago and got a pelican with a "change pelican color" button: https://static.simonwillison.net/static/2026/hy3-preview-pel...
Tony the Tiger on a bicycle selling addictive items to children is not new.
Re: Hy3
#55Novita is offering free Hy3 on OpenRouter until July 21st
Re: Hy3
#56Got really excited for a minute that the long-standing [Hy](https://hylang.org) project had had a release, but it's just some confusingly-named LLM. Shame.
Re: Hy3
#57A month ago I wrote a blog post about how Hy3 was topping the OpenRouter rankings despite no one talking about it: https://news.ycombinator.com/item?id=48317294 As of today, it has fallen to 8/9th on the rankings. I don't see a reason where you would use this model over competitors. However, price economics are bit confusing, as currently the effective input price of Hy3 via OpenRouter is now the same as DeepSeek-hos…
That was the preview model right? This one appears to be significantly better.
I mean it's still a small model, but at least the benchmark scores (incl. on DeepSWE) went up significantly.
It costs as much as Flash, but the benchmarks are on par with Pro (or above in some cases).
Of course, benchmarks are mostly meaningless -- the only real benchmark is the actual work you give it :)
Re: Hy3
#58A month ago I wrote a blog post about how Hy3 was topping the OpenRouter rankings despite no one talking about it: https://news.ycombinator.com/item?id=48317294 As of today, it has fallen to 8/9th on the rankings. I don't see a reason where you would use this model over competitors. However, price economics are bit confusing, as currently the effective input price of Hy3 via OpenRouter is now the same as DeepSeek-hos…
Writes pretty engaging prose, finetunes well, now MIT licensed... what's not to like?
Oh and very good world knowledge for the size: better than than DS4 Flash
Re: Hy3
#59I would never use any product that can't explain on its own front page what it is and why I should use it.
It's like a computer, but you can talk to it.
Re: Hy3
#60A month ago I wrote a blog post about how Hy3 was topping the OpenRouter rankings despite no one talking about it: https://news.ycombinator.com/item?id=48317294 As of today, it has fallen to 8/9th on the rankings. I don't see a reason where you would use this model over competitors. However, price economics are bit confusing, as currently the effective input price of Hy3 via OpenRouter is now the same as DeepSeek-hos…
It is really slow on openrouter and I ran into many http errors.