Hacker News: girvo

New comment by girvo in "Claude reveals ECDSA curve origins"

girvo — Fri, 16 Oct 2026 20:29:34 +0000

We already have controls for that: we control access to the reagents and equipment needed. Yknow, like we always have.

Information is not dangerous. This is a ridiculous argument to me, but maybe my chemistry degree has me biased.

New comment by girvo in "Why is every rationalist blog post way too long?"

girvo — Thu, 15 Oct 2026 00:42:58 +0000

It’s absolutely addictive, anyone who says otherwise is suspect

What I take issue with is the original sentence saying it’s “bad for you”, I was expecting new science showing that it’s, well, bad for you rather than “just” addictive

New comment by girvo in "We’re releasing Jev 1.14.0 along with experimental features for dreamers"

girvo — Wed, 14 Oct 2026 23:02:35 +0000

They are? In all my evals at work, Jev seems to win, despite me wanting the open weight versions to.

I imagine if I fine tuned one of the open weight models for my use case it would be possible to beat it, though, but as a general drop in decision model, I’ve not really seen much that beats it especially for the cost

New comment by girvo in "Redesigning source control at Anthropic"

girvo — Wed, 14 Oct 2026 12:45:28 +0000

But the first version was “mostly handwritten”?

New comment by girvo in "Redesigning source control at Anthropic"

girvo — Wed, 14 Oct 2026 12:41:50 +0000

That’s what I’m seeing too. It’s depressing. I hope I can pay off my house in time to go do something else.

New comment by girvo in "Why is every rationalist blog post way too long?"

girvo — Wed, 14 Oct 2026 12:10:25 +0000

And “bad for you” is left completely unexamined. It feels very dishonest to me, and it’s a shame because I was hoping to learn something new.

New comment by girvo in "Why is every rationalist blog post way too long?"

girvo — Wed, 14 Oct 2026 11:33:26 +0000

It is? Am I getting a different link to you, or is my reading comprehension just terrible at 9.30pm or something.

https://psychotechnology.substack.com/p/a-love-song-to-nicot...

It says the exact opposite to me?

New comment by girvo in "Why is every rationalist blog post way too long?"

girvo — Wed, 14 Oct 2026 11:31:17 +0000

> It turns out, actually, nicotine is addictive, and is bad for you even if you don't smoke it, as you probably already obviously knew.

This is not the point, but I’m very confused by the link that is linked as evidence on that line? It doesn’t match the sentence it’s attached to

Link in question: https://psychotechnology.substack.com/p/a-love-song-to-nicot...

New comment by girvo in "New Apple TV 4K"

girvo — Wed, 14 Oct 2026 08:02:32 +0000

> which Apple finally put in their new device

Not to take away from what you're saying, but I have a 2022 Apple TV 4K with a gigabit ethernet port.

You just had to buy the higher storage model, weirdly.

Model MN893X/A

New comment by girvo in "Gemini 4 Argon"

girvo — Tue, 13 Oct 2026 20:06:00 +0000

No, and anyone who says otherwise is being silly.

It’s still damned capable though, I’ve done a crazy amount of good work with 5.3 Flash.

New comment by girvo in "Citroen revives the 2CV for an electric age"

girvo — Tue, 13 Oct 2026 06:48:09 +0000

My 2007 Suzuki Swift felt horrible at 130km/h or above!

New comment by girvo in "AI Is a Tool. Using It Well Takes Skill."

girvo — Mon, 12 Oct 2026 22:35:08 +0000

For now. It is definitely true right now, there's a notable difference between my coworkers depending on their skill driving these models: it mostly seems to be correlated with those who are willing to build their own tools, now that the cost to do so is basically zero.

But the models are getting so good and so fast, that I'm starting to wonder if that will stay true forever... probably not, if I had to guess. I'm just trying to pay off my house as quickly as I can...

New comment by girvo in "Muse Wonder"

girvo — Mon, 12 Oct 2026 22:16:56 +0000

Would they not have RL'd Claude such that we picked the one most likely to not complain and emit those stop tokens? Otherwise they wouldn't be useful. Seems flawed...

New comment by girvo in "Doory – Open-Source Canva"

girvo — Mon, 12 Oct 2026 08:38:11 +0000

No, that’s just standard AI generated nonsense marketing prose

New comment by girvo in "Artificial Insanity"

girvo — Mon, 12 Oct 2026 00:13:08 +0000

Sure, if you think so, but discussing or arguing for/against those points here is far more interesting than the done-to-death stochastic parrot stuff.

New comment by girvo in "Artificial Insanity"

girvo — Sun, 11 Oct 2026 21:17:10 +0000

I really wish the article in question hadn’t used that phrase, because you’re right. But the rest of the article is also correct in the dangers facing us from this technology as an accelerant regardless, and I think it’s much more interesting to talk about that: but this entire comment thread will dunk on the stochastic parrot paragraphs instead.

The funny thing is though, I think it’s an in group signalling mechanism. You need the anti-AI crowd to know that you’re anti-AI, and this is a rapid way of doing so, to get it upvoted here.

New comment by girvo in "500B tokens later: Letting AI agents decompile a first-person shooter"

girvo — Sun, 11 Oct 2026 02:44:41 +0000

> they also commit to keeping private

Reading between the lines:

"The avid reader of my blog might have noticed that I had previously written two posts that have since been removed. Everyone else might now be wondering which game I am talking about. To both of you I can only say that corporate America was here to ruin our fun."

Keeping it private likely wasn't the original plan...

New comment by girvo in "Microsoft-Decision-1, our model for fast decision-making"

girvo — Fri, 09 Oct 2026 20:52:07 +0000

That’s fascinating, but not that surprising to me. We act like quantisation is free “Q8 is basically lossless” is often said in the local LLM community, but it really isn’t. The trade offs are worth it, personally, and the damage to coding ability seems low: decision model approaches are stricter though

Super cool finding!

New comment by girvo in "Typesafe AI raises $870M at $7.5B"

girvo — Fri, 09 Oct 2026 20:41:27 +0000

Counterpoint: my work has already allowed us to call and test Jev. Those others? Who knows when, if ever.

New comment by girvo in "Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter"

girvo — Fri, 09 Oct 2026 12:45:29 +0000

Earlier this year, Step 3.5 Flash and then Step 3.7 Flash were easily my favourite local models. Step 5 is far too large to run on my DGX Spark-like, but I’m excited to try it out. It’s benchmarks look promising, and I’m hoping it’s a lot faster than GLM is