haolez

Joined 9 years ago

Karma
4,382
Submissions
1,486
Member since
Apr 15
Gmail: ivan.reche Discord: ivarec
View on Hacker News

Recent submissions

Comment · 2 days ago
Yeah, I thought it was just me - it hallucinates more than Flash, Flash-lite and Pro.
Comment · 10 days ago
It's literally called _soft_ware (vs. hardware).
Comment · 11 days ago
I don't want to bore my HackerNews fellows, so I'm sorry in advance, but wasn't there a lot of drama in the Nix community? I've read some time ago that a private company was buying parts of its infrastructure (or something like that) and forcing some changes upstream and people were not happy about it.

I'm interested in NixOS, but I'm at an age where I just want things to stay stable and change only when they really have to. I already have a lot of big mandatory changes from life itself, I don't need more :)

I'm writing this in good faith. I'm genuinely curious and interested in trying it again.

Comment · 13 days ago
But the chain of thought as text can be elusive, no? It might not be related with the actual "reasoning" of the model. There was a paper about this.
Comment · 16 days ago
I feel that a desktop like this would just occupy parts of my cognition for no good reason. Not sure.
Comment · 1 month ago
If you use an LLM to write assembly, it is officially your (optimizing?) compiler :)
Comment · 1 month ago
I'm not saying that Big Tech won't respect it. I'm saying that, if privacy and intellectual property is a major concern for your company, you can't trust a checkbox - you have to keep the data in-house.

Most companies won't have this level of risk aversion (maybe defence?).

Comment · 1 month ago
It's naive to think that the check boxes in the other providers will protect your data.
Comment · 1 month ago
Nice work!

Are you sure this isn't just a custom model that is API-compatible with OpenAI?

Comment · 1 month ago
Better metric: your LLM enhanced version cannot be larger than the prompt. Otherwise, you are just reducing your signal to noise ratio.
Comment · 1 month ago
I think the problem is the ease that you can create believable low effort articles and even software.

It's harder to filter for the good stuff when compared to previous hypes, like Blockchain and JavaScript frameworks.

Comment · 2 months ago
That's an interesting viewpoint, but then, will the allocator's performance never matter for any use case that is not "wrong"? It doesn't feel right.
Comment · 2 months ago
Yep. Early in my career I developed a simple driver for a CAN interface to be used in a medical device, which was my assigned project.

The same code was used in another project of this same company. The project was a missile. It felt weird.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton