Hacker News: hassaanr

New comment by hassaanr in "My favourite PowerMac is a Nintendo Wii"

hassaanr — Fri, 30 Oct 2026 19:03:23 +0000

Yes but mostly not. Modern MacOS is based off of NeXTSTEP OS from the NeXT acquisition, not classic.

New comment by hassaanr in "Performance per dollar is getting faster and cheaper"

hassaanr — Sat, 04 Jul 2026 10:05:26 +0000

You’re right, but this poses a separate issue as the providers then do FP4 PTQ, which is quite lossy. Reduces the model size and optimizes for Blackwells at the (imo severe) cost of performance.

New comment by hassaanr in "Performance per dollar is getting faster and cheaper"

hassaanr — Sat, 04 Jul 2026 03:50:06 +0000

While cool, quantization to FP4 is practically never lossless in actual use. A lot of providers are advertising high TPS on Kimi and GLM, but the models are functionally lobotomized and no longer close to frontier quality. Would love to see this not be true.

New comment by hassaanr in "Running a Minecraft Server and More on a 1960s Univac Computer"

hassaanr — Tue, 21 Apr 2026 21:23:11 +0000

Incredibly cool project and fantastic write up!

New comment by hassaanr in "I ported Mac OS X to the Nintendo Wii"

hassaanr — Wed, 08 Apr 2026 18:59:38 +0000

In love with projects that are done solely because 'why the hell not'. Fantastic writeup and work.

New comment by hassaanr in "Ask HN: Share your personal website"

hassaanr — Thu, 15 Jan 2026 17:34:29 +0000

https://www.hassaanraza.com/

New comment by hassaanr in "Electric cars produce far less brake dust pollution than combustion-engine cars"

hassaanr — Thu, 24 Jul 2025 05:15:09 +0000

engine braking does not have any effect on the clutch, other than while downshifting, which if you're blipping/rev-matching has practically no effect

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Fri, 04 Oct 2024 20:33:53 +0000

Also to add- the one service that was fast enough on the LLM side was Cerebras. The time to first token (ttft) is incredibly fast (200-300ms) and the t/s is 2000t/s for 8B- combined making for a great conversational experience.

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Fri, 04 Oct 2024 20:29:40 +0000

Please try it again when you get the chance! We were dealing with high load the past few days and are good to go again! Re: head movements, I totally agree; natural head movements are really important to make it feel more natural. The issue is controllability today, which is something we're working on as well!

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 15:55:21 +0000

Oh no- what issue were you facing with Hassaan bot? It might just have been getting the hug of death. Hope you can try again!

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 05:41:05 +0000

If you use the demo on the website you don’t have to enter an email, tavus.io

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:42:45 +0000

Thanks friend! Great to hear- let us know how we can help in any way :)

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:40:50 +0000

This is definitely a good idea! I think the hard part is making it contextual and relevant to the last question/response, in which case the LLM comes into the equation again. Something we're looking at though!

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:37:24 +0000

Totally- as programmers we're so used to communicating via text and meeting computers where they are- it's easy for us. However, we're the minority in the world! I think most people who are not us want to communicate like they do with others.

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:34:25 +0000

This is good feedback. We have a base subscription fee to cover ongoing costs of maintaining the models/replicas you create and other elements, otherwise it's all on-demand.

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:30:38 +0000

Sorry about that friends- we had a hug of death event. Hope you can try again!

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:30:08 +0000

Haha great question- we're really passionate about the conversational video interface, and our goal is to make it /incredibly/ good, so we're going to continue to do research and release new models that accomplish this. There's so much to do in the pursuit of that.

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:26:32 +0000

Glad you had a good conversation :) The Hassaan version has a lot more background filled in- actually my entire website is it's context, so he has more interesting things to say!

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:25:43 +0000

Apologies about the seduction- I promise I'm not like that in real life.. Re: pronunciation, this is something we're working on improving!

New comment by hassaanr in "Show HN: A real time AI video agent with under 1 second of latency"

hassaanr — Wed, 02 Oct 2024 04:22:50 +0000

We might need to do a better job of explaining this- but this is true. You retain ownership of your data and we don't sell or use it (other than to train your specific clone that you can delete at any time). Personally, I think too many AI companies are playing fast and loose in this space, so I get the concern. We want to do it right.