aerhardt

Joined 3 years ago

Karma
1,367
Submissions
485
Member since
Feb 11
Alex Erhardt https://www.alexerhardt.com
View on Hacker News

Recent submissions

Comment · 3 days ago
Saving this - I’m hoping to decompile SimGolf to play it on my Mac!
Comment · 4 days ago
My M1 MacBook Pro has been the best hardware investment I’ve ever made. I had planned to update it in 2025 at the four year mark, but it’s still going strong so I don’t see a reason. The new plan is to go to the Apple store the very day that it dies.
Comment · 12 days ago
> There's a ton of magical thinking out there where people seem to assume AI will progress right up to the point where it is maximally beneficial to their job without replacing them. Keep huffing that copium, folks.

Because you are singularly right about the issue? Have some intellectual modesty, brother.

Comment · 12 days ago
There are many of us who enjoyed coding, and who enjoy the new paradigm, too.
Comment · 1 month ago
He sold $20 worth of lemonade the other day, which comes to about $175k annualized.

What's your ARR, anyway?

Comment · 1 month ago
I haven't done it in a production project - this will be the first time for me. I have specified the architecture and data definitions pretty well. The tests will be run against the customer's Excels, which is what the warehouse will be replacing. I'll check the general shape of pipelines, models, orchestration code, etc. but in many parts I probably won't review the code myself.
Comment · 1 month ago
I've used Astra, Fable 5.1, Sol 5.6, Opus 5. They're definitely making progress and the proof is in the pudding - I reach for the most advanced model as much as I can. But I wouldn't say their capabilities have increased dramatically. I use it for both coding and non-coding workloads and I don't feel I can do anything dramatically different. Again at the end of the day this is a debate on semantics because we can have very different definitions of "dramatic improvement".

(I'm not factoring the benchmarks into the discussion, because I've never quite cared about them)

Comment · 1 month ago
I still develop in smaller chunks, checking nearly all the output. However I have a work project (building the warehouse and BI for a client) that is well-specified and where I will try to few-shot the development. Hope it delivers.
Comment · 1 month ago
I really enjoy the balance of speed and accuracy of Astra. I can definitely see it become my driving model for most tasks, technical and non-technical.

However, I don't see it as such a massive leap compared to Fable or Sol. As ever, there's a mismatch between the benchmarks and my daily experience of the models.

What do you all think about Astra now that it's been out for a few weeks?

Comment · 1 month ago
Is this your idea of an intelligent contribution to the conversation?

There is plenty of evidence in the article from real professors at real universities (ex: Princeton), saying that they’ve had to dramatically cut reading workloads from humanities courses. I’ve heard similar things from European universities.

Other hard evidence is in plummeting reading comprehension scores in many countries that participate in PISA.

In the States, there is plenty of other stats that point that students are below their expected reading grade - the worse in generations.

And all you have to contribute is that this is “idiotic”? The irony. Inform yourself.

Comment · 1 month ago
Comment · 1 month ago
Comment · 1 month ago
It's a load-bearing poster.
Comment · 2 months ago
Sorry for defending Aristotle? Have we lost the plot as a society?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton