Hacker News: ygouzerh

New comment by ygouzerh in "Gemini Omni 1.1 Flash"

ygouzerh — Fri, 28 Aug 2026 03:15:11 +0000

No worries, even on chromium, their webpage is just horrible. They seems to have focus only on mobile reading, on desktop its a mess.

New comment by ygouzerh in "GLM-5.3-Flash"

ygouzerh — Wed, 26 Aug 2026 17:52:08 +0000

You can use OpenRouter directly in Claude Code as well, it's quite nice!

New comment by ygouzerh in "Show HN: I made a Raspberry with Qwen my local car AI"

ygouzerh — Wed, 26 Aug 2026 10:39:31 +0000

For prompts that needs fact-checking, I like these days to use Perplexity directly instead these days. It's way faster than the default websearch tool + give a link to the reference directly.

New comment by ygouzerh in "Show HN: I made a Raspberry with Qwen my local car AI"

ygouzerh — Wed, 26 Aug 2026 10:37:22 +0000

You could hook it up with different tools, like real time information:

Oil + GPS + Web Search --> "LLM > You have 50 Km of autonomy. You can go today to this cheaper oil station, at 20 km, on your GPS road, instead of the one near your home. The one at 10Km is closed as well due to a local strike, I will avoid it too"

You can of course script all the scenarios + only use a TTS model. However, when plugging different systems together, I feel that it's the sweet spot where LLM is shining --> no need to pre-plan every scenarios that the user will ask, it can be done on the fly

New comment by ygouzerh in "Show HN: I made a Raspberry with Qwen my local car AI"

ygouzerh — Wed, 26 Aug 2026 10:30:20 +0000

I feel that it could be a nice addition for:

- People that didn't read the manual (actually almost all of us), like: explain a warning signal

- Or integrate different systems together: `I saw that on your GPS you want to go to this place, but in 2 hours it will be snowing heavily there. Please remember to bring your snow chains'

New comment by ygouzerh in "c100"

ygouzerh — Fri, 21 Aug 2026 16:27:19 +0000

I felt as well that they miss their window. This kind of rectangular shape with keyboard + computer would be great actually for digital nomad / people going to coworking spaces, but looks way to heavy.

New comment by ygouzerh in "Show HN: Huzzah – a novel approach to coding with AI"

ygouzerh — Fri, 21 Aug 2026 08:22:02 +0000

I don't think we need to wait 5 years, we can already see it know

New comment by ygouzerh in "Show HN: Huzzah – a novel approach to coding with AI"

ygouzerh — Fri, 21 Aug 2026 08:20:31 +0000

Same, I am still thinking that it's a parody: going full loop back to programming

New comment by ygouzerh in "Nvidia Nemotron 3.5 Lightning and NeMo Switchyard"

ygouzerh — Wed, 12 Aug 2026 04:43:44 +0000

This resonates well with engineers: making something complex is easy, making them simpler is harder

New comment by ygouzerh in "What Happened to HackerOne?"

ygouzerh — Mon, 10 Aug 2026 09:10:29 +0000

This one looks shocking on the outside indeed! It's however a sales HR practice: lower salary and commission, but use the alluring treat that top performers will have a special exclusive trip at the end of the year. Many are crazy for it.

It's more a reward for a competition-style work mindset.

New comment by ygouzerh in "The Philippines' big offshoring industry is growing despite AI"

ygouzerh — Mon, 10 Aug 2026 07:46:43 +0000

> It seems like AI has incidentally commoditized the complement (procedural knowledge), and in turn created greater demand for inputs like human judgement and "empathy".

I think as well there is currently the following: AI still needs an operator, in the same way than a bulldozer needs a bulldozer operator. And like with bulldozer, there are always something that business stakeholder wanna dig, now that digging is faster.

New comment by ygouzerh in "Mistral's Shieldstral: 3B open-weights model for multimodal moderation"

ygouzerh — Wed, 05 Aug 2026 03:40:35 +0000

Crazy that it's a small lab becoming the frontier in term of moderation models, instead of Meta which is pouring dozens of billions into LLMs.

Meta would really benefit from work done on this front, however their model Llama Guards are quite lagging compared to the competition.

New comment by ygouzerh in "Xiaomi-Robotics-1"

ygouzerh — Mon, 20 Jul 2026 08:02:20 +0000

Small sharing tips, in case it can help: have the maximum of hangers possible. It take a bit more space, but the time saved is huge + it remove iron time for low wrinkle sensitive clothes (e.g cotton polo)

New comment by ygouzerh in "Xiaomi-Robotics-1"

ygouzerh — Mon, 20 Jul 2026 07:58:40 +0000

I will suggest mix of both: some everyday tools are already built for being used with hands and legs (e.g opening a door). But indeed adding some different grip types, additional arms, etc, could be helpful.

New comment by ygouzerh in "Chatto is now open source"

ygouzerh — Thu, 09 Jul 2026 03:11:27 +0000

What are the pros and cons versus Rocket.Chat?

New comment by ygouzerh in "GPT‑Live"

ygouzerh — Thu, 09 Jul 2026 01:49:46 +0000

So true! I am not sure if it was on purpose that the model spoke with a so strong accent!

New comment by ygouzerh in "Monetization Gateway: Charge for any resource behind Cloudflare via x402"

ygouzerh — Wed, 01 Jul 2026 17:30:33 +0000

Actually, x402 was created because using a credit card programmatically is very difficult.

The whole business of Stripe is based on that: it's so hard for developers to do, and so many regulations, that they would rather pay an another company to do so.

Crypto can be sent just using a contract.transfer() call

New comment by ygouzerh in "Monetization Gateway"

ygouzerh — Wed, 01 Jul 2026 17:27:47 +0000

It seems the usage will be mostly agent <-> service or service <-> service. For user, probably using a Metamask-like wallet yes

New comment by ygouzerh in "Monetization Gateway"

ygouzerh — Wed, 01 Jul 2026 17:25:49 +0000

An partnership with Perplexity AI would be nice!

Let's say a part of the subscription is used to pay for it.

New comment by ygouzerh in "Monetization Gateway"

ygouzerh — Wed, 01 Jul 2026 17:23:58 +0000

Their example of an /api/premium is quite nice! You could you like keep existing pages free, but provide specific output content for llm!

So if: cost monetized API < cost configuring scraper for your website OR feature provided by premium api > data got by scraping, then some people/business will likely pay