I'm a honeycrisp fanatic (and it's a good balance of sweet/tart for me). This is the first I've heard of Sweetango, I don't think I've seen them in the grocery stores. Will be keeping my eyes peeled.

Unlike many other apple varieties these days, SweeTango are only available in traditional "apple season" (Autumn months through November in the USA). I've long been a fan of HoneyCrisp, so I tried SweeTango, and while it was quite good, I still prefer HoneyCrisp. I had a similar experience with Cosmic Crisp--not as good as HoneyCrisp, but nice for some variety.

Just a heads up -- the key in your header seems to link to a compromised/spam site.

.

It's been years now and that's still little more than a conspiracy theory. I don't think it has much bearing in real world policy discussion.

What a weird tone this is written in.

I think it is intended to sound like Sam Altman. Would look exactly like a tweet of his if it didn't have capitalized characters.

A couple of years ago now.

I asked it to write a script that would search for a specific string in footers in a massive series of DOCX files and change them according to some rules. The strings ended up being embedded in cells within an invisible table in the footers, the LLM realized this and switched strategy to a full deep traversal of the underlying XML. It correctly processed like 50 of these files in about 10 minutes, using libraries I wasn't aware of. I had spent an hour being annoyed before trying.

It was an "oh shit" moment for at least that category of work.

I'm curious to find out if they're using a model to detect AI content. I'd be more amused than disappointed. But, alas, potato.

I got a partial load and what it looks like it does is just search each submission for a list of key words and discards any that hits, so it would discard this submission.

I would argue that in a small way, this post _is_ about AI, so it wouldn't be a false positive.

I was not suggesting that it would be a false positive, I was suggesting that this will filter out many submissions that would be of interest to those that want less AI on HN. This would flag a blog that has nothing to do with AI if some random person mentioned AI in the comments of that blog post, right?

It's not an LLM.

Why use big program when regex do trick?

You can get the best of both worlds with a small embedding model

Show me an embedding model that runs as fast as an optimized regex engine and I'll buy you a beer.

Probably not as fast as a simple regex but static embedding models can get stupid fast e.g https://www.flowercomputer.com/news/fast-static-embedding/

Master of efficiency

Yeah, this is their "live reporting" feed, where updates and context get posted about an in-progress event.

I don't think you'll find that type of language in the more traditionally published/edited articles.

The contents are confidential. They are just announcing they submitted it.

Could you elaborate a little on what you are doing with 40-50 agents? I use Claude, I've employed sub-agents, but I still can't wrap my head around how people are using them to that extent.

ha, I didn't mean they are all running at the same time. sorry if it sounded like this. I open a new worktree/agent session for each new feature or bugfix. Usually I start with ideation and brainstorming before doing the actual implementation. However my priorities shift daily, so I could be starting a feature on monday, but then stop during the ideation already, pick up another task on tuesday and won't go back to the initial one until a week or a month later. Since I got it in a neat worktree in superset, I still see my open branches easily, have access to its claude code session and can resume the work much easier than before having terminal tabs. Because of this setup I currently have 17 backend sessions, 25 frontend sessions, plus several other repos open and ready, when i need to.

Ahh got it, thanks. That makes a lot more sense -- indeed I thought you had 40 active, parallel sessions!

The form factor is indeed strange. It reminds me of an N-Gage if they had a "rugged"/durable version that was made for construction sites.