Hacker News Reader

Comment by asdfman123 | Hacker News Reader

I've been using it for a while internally at Google. I prefer Argon over Opus 5.5 because of the clear thinking and directness. It phrases things in an organized, straightforward way.

View on HN

Interesting. My favorite LLM output ever was the reasoning traces in gemini 2.5 pro. I found them much easier to understand than the "final output", because they were very structured and concise. Of course, they ended up hiding the reasoning, not long after that, like everyone else... sad!

Same here, especially the march edition. It was incredible. I thought Google will run away with it.

I haven't tried Argon, but for writing, I actually prefer 3.8 Flash over any GPT and Opus.

If true, this will be a gigantic departure from any model Google have released to date. I’m hopeful but also pretty skeptical.

I feel Argon is about as good as Opus 5.5 but I find Opus annoyingly sarcastic and incomprehensible.

I know it's a matter of personal taste but it reminds me of a grad student that tries to sound smarter than he is by being dismissive and opaque.

Opus 5.5 has the personality of a proud righteous nerd, definitely incomprehensible at times, unless you explicitly tells it to slow it down, it crams information far too dense.

Great model to architect and resolve eng. problems in a harness loop tho. Poor handoff.

So its clearly trained on Stackoverflow.

Yes, exactly! Maybe not sarcastic but definitely using jargon and being opaque like we all know it, it’s just hinting. Feels like talking to someone who’s constantly trying to prove to me they are smart(er).

The thing is that if you do know what it's talking about then it gets you the information the quickest that way. If you're not an expert you can always ask it to explain. I don't want it to ELI5 by default.

That's not my experience, the model is adding tons of unnecessary details, that make it much harder to find the important information for an expert that already knows all those details.

I don't want ELI5, I just want the model to go straight to the point, like a colleague human expert would do.

I don't know, that's exactly what Opus 5.5 feels like to me.

Not my experience either. I find it both verbose and obscure, in its comments or explanations. It also oftentimes assumes that I know what I don't and that I ignore what I actually know.

Agree I do not like the way Opus 5.5 communicates with me. It feels like it is trying to act superior in a condescending way. DO NOT LIKE. I have not used Argon yet but Gemini 3.8 Flash has been a joy to use in comparison (and so fast!) as a daily driver.

>...trying to act superior in a condescending way...

Strange. I wonder why? Have you adjusted 'roles', added 'ask clarifying questions'? This is most peculiar.

Yes! Literal copy paste from my session with Opus 5.5 this morning:

> You gave me a long answer but it didn’t answer my question: can we safely remove $X

Sarcastic? wdym?

Opus has no sense oh humor at all. I wish mine was sarcastic.

I have used it as well. It is very dense, but it cites with evidence and has a direct and straightforward approach and manner. It doesn't really have a "tone" or mannerisms the way Opus 5 did. It follows instructions and sticks with pretty clean language by default. Argon is solid and handles long horizon well.

Reply on news.ycombinator.com