earino

Joined 16 years ago

Karma
790
Submissions
145
Member since
May 25
Codito ergo sum.
View on Hacker News

Recent submissions

Comment · 1 month ago
Basically ibs. Incredibly unpleasant bathroom urgency is the way I would describe it.
Comment · 1 month ago
I think that's a pretty good guess. I move around different countries a lot so I also assume I can look like a bot farm from multiple source IPs.

However at this point I talk to LLMs more than anyone except probably my wife. As a multiple times immigrant, I can absolutely believe I'm adjusting my speech patterns to its vernacular.

Comment · 1 month ago
Comment · 1 month ago
The base-model criticism is fair. Laya is weak zero-shot and doesn't have the world knowledge of a much larger pretrained model. Their own site puts the base models at around 0.35 on the typed-decisions benchmark, which is close to random.

I don't think that makes it a dead end. Laya is designed to be fine-tuned for a specific task, and the site reports the fine-tuning gains. The 0.766 number comes from fine-tuning on the benchmark's train split, not from the base checkpoint. They also report that fitting a single temperature scalar per question type cuts expected calibration error from 0.466 to 0.081. That's a large gain, and it only shows up after you specialize the model.

"Peer" is doing a lot of work in that comment. Jev can take on a new task without retraining because it starts with far more knowledge; Laya trades that away to stay small and trainable for a fixed task. So I wouldn't compare base Laya to Jev and stop there. Compare Jev to fine-tuned Laya on the same task and test set, then look at accuracy, latency, cost, calibration, and robustness, depending on which of those matter for the deployment.

Comment · 1 month ago
Ox bile supplementation was my biggest quality of life change after having my gall bladder removed. I unfortunately waited over a miserable decade before discovering it. I strongly encourage anyone who has had their gall bladder removed to look into this.
Comment · 6 months ago
Claude going down is how I know I can start messaging with my west coast friends.
Comment · 6 months ago
Hello Boris! How do I increase the 1 hour prompt cache window for the main agent? I would love to be able to set that to, say, 4 hours. That gives me enough time to work on something, go teach a class, grab a snack, and come back and pick up where I left off.
Comment · 9 months ago
Comment · 9 months ago
What joy to bump into you in the comments section! I definitely preferred 5 minutes past, but my calendar was pretty awful.

What was really awful, however, was when your calendar was a random mishmash of starts at :00, :05, :30 and :35 :-)

Comment · 1 year ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton