Hacker News: yfontana

New comment by yfontana in "My personal AI agent posted my bank details on company Slack"

yfontana — Sat, 10 Oct 2026 15:11:25 +0000

but a Slack channel, maybe

New comment by yfontana in "REA Reverse – Engineer Anything"

yfontana — Sat, 10 Oct 2026 13:13:25 +0000

GLM 5.3, an open model, is also quite good at reverse engineering.

New comment by yfontana in "Getting the most out of Opus 5.5 in Claude and Claude Code"

yfontana — Sat, 03 Oct 2026 21:28:40 +0000

A significant part of it is that with Opus 5.5, cache reads are priced at 5% of inputs, instead of 10% for previous models.

New comment by yfontana in "Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms"

yfontana — Mon, 28 Sep 2026 22:32:31 +0000

Jev is a classifier. The big thing about it is that it has high accuracy on domains it wasn't fine-tuned for, like an LLM, but with speed and cost comparable to traditional classifiers.

New comment by yfontana in "Salesforce Global Outage"

yfontana — Thu, 17 Sep 2026 21:52:04 +0000

> in this case tracking sales pipelines

Salesforce does a lot more than that

New comment by yfontana in "Nike exits the S&P 100 after 18 years and a $200B market-cap wipeout"

yfontana — Mon, 14 Sep 2026 08:44:41 +0000

There are still plenty of shoes that will last for a while. You just need to avoid the super-light ones. Those are designed to go fast, not to be durable.

New comment by yfontana in "The Mysterious Syndrome Destroying Endurance Athletes"

yfontana — Mon, 17 Aug 2026 15:21:46 +0000

That particular issue is known as RED-S: https://en.wikipedia.org/wiki/Relative_energy_deficiency_in_...

But over-training can happen even with sufficient nutrition (even if it is less likely, as nutrition is a major part of post-exercise recovery).

New comment by yfontana in "The Mysterious Syndrome Destroying Endurance Athletes"

yfontana — Mon, 17 Aug 2026 15:15:05 +0000

This article was written in 2015. Nowadays most elite ultra-runners do have coaches, and follow data-driven training regimes. This is a trend in all professional (and, to a lesser degree, amateur) sports, but it is definitely quite noticeable in a sport where athletes used to basically be dudes and girls who liked running fast in the mountains and did that a lot. A lot of that data-driven training is aimed at maximizing training load without going into overtraining.

As a result of this and other optimizations (most notably higher carbs consumption during races, but also better heat training, better recovery protocols, better shoes, etc.), races keep getting faster. The article mentions the course record for the WS100 dropping by 50' between 2004 and 2012. Since then, it has dropped by another full hour (13h46 this year).

New comment by yfontana in "Qwen3.8-2.4T"

yfontana — Thu, 13 Aug 2026 13:01:37 +0000

If what China has been doing is considered generous, then so should the tens of billions in foreign aid that the West has sent to the South over the years.

I'm not saying that China's investment in the South hasn't had positive effects. But "generosity" is rarely a relevant lens when analyzing international relations.

New comment by yfontana in "Qwen3.8-2.4T"

yfontana — Thu, 13 Aug 2026 08:05:03 +0000

China has been using that rhetoric of "helping" the global south ever since it emerged as a super power. In most cases, it has a lot less to do with generosity than with securing natural resources and international influence.

New comment by yfontana in "Lovable raises $400M Series C"

yfontana — Thu, 13 Aug 2026 07:47:17 +0000

My personal mental model is that this is the AI version of the low-code web app tools that have existed for a while (like Outsystems, Power Apps...). Those tools are a bit of a nightmare for devs to work with and they have all sorts of limitations. Yet they still carved themselves a fairly significant niche in the market, as they allow building apps fairly quickly and cheaply... as long as you stick to simple apps. I don't know if Lovable will be able to capture that market, but that's how I try to make sense of this.

New comment by yfontana in "Honey, I shrunk the embeddings: Matryoshka vs. PCA"

yfontana — Sun, 09 Aug 2026 21:21:08 +0000

That sentence is written as an introduction to an article about embeddings compression. So yeah, it does take a bit of a shortcut from "search" to "vector storage", but that's irrelevant to the rest of the article.

New comment by yfontana in "Taxi drivers rarely die of Alzheimer's"

yfontana — Sun, 09 Aug 2026 20:48:19 +0000

Something interesting that the original study looked at, but isn't mentioned in the linked article: this effect was not observed for non-Alzheimer's dementia deaths. There seems to be something specific to spatial reasoning and Alzheimer's.

New comment by yfontana in "Taxi drivers rarely die of Alzheimer's"

yfontana — Sun, 09 Aug 2026 20:44:32 +0000

> "Become a cabbie" is NOT an intervention that is going to help whatsoever.

How about promoting spatial awareness and reasoning exercises (which is the actual suggestion of the article)?

New comment by yfontana in "Mario Meets Pareto"

yfontana — Fri, 07 Aug 2026 09:56:32 +0000

For me (Firefox on Windows, not in reader mode) the graphics stop showing at the "585 builds" paragraph.

Besides, if something doesn't work in reader mode, it's also likely to not work with screen readers. People who use those don't have much of a choice in what they can enable or not.

New comment by yfontana in "Mario Meets Pareto"

yfontana — Fri, 07 Aug 2026 09:49:31 +0000

It's cool until it breaks halfway through on Firefox, making the page unusable in that browser.

New comment by yfontana in "Kimi K3: Open Frontier Intelligence"

yfontana — Thu, 16 Jul 2026 16:05:32 +0000

How come no other big model seems to be able to deliver the same type of extremely low cache cost though, if their techniques are public?

New comment by yfontana in "Leanstral 1.5"

yfontana — Wed, 01 Jul 2026 08:43:01 +0000

That act applies just as much to those American and Chinese models within the EU.

New comment by yfontana in "I used Claude Code to get a second opinion on my MRI"

yfontana — Mon, 29 Jun 2026 09:38:04 +0000

Yeah, medical computer vision is a (fascinating) field with a lot of ongoing research. SOTA models are highly specialized, and are only getting good enough to be used by actual doctors and patients. Using a general purpose LLM to do this is similar to giving a credit card to Openclaw and telling it to make you rich through the stock market & cryptos.

New comment by yfontana in "GLM 5.2 beats Claude in our benchmarks"

yfontana — Mon, 29 Jun 2026 09:08:44 +0000

Doesn't track with mine. I've been stuck with Sonnet 4.6 with one of the clients I work for. It writes code fine, but it's not nearly as good as the more recent models for everything else. It's fairly common for it to suddenly go off the rails for no good reason, so I can't really trust it with agentic loops. It's also not very good at diagnosing non-trivial issues. It's not uncommon for it to suggest whole lists of irrelevant / nonsensical reasons for something not working. Then I copy/paste the code and some context into chatgpt and it hones in onto the correct issue right away, even with inferior tooling.