Recent submissions

Comment · 2 days ago
I spent way too much time on this, but hey, I'm now a Tier 1 ISP!
Comment · 13 days ago
You might not have a choice. For example, if you want to get a guarantee from Anthropic that they don't train bases on your prompts, you will need an enterprise deal, which is pay-by-token.
Comment · 27 days ago
I think you could do that already. Just store your weights in a table...
Comment · 1 month ago
Luckily this depends on manufacturer. I've been buying La Sportiva BoulderX approach shoes for around 10 years. I have like my 7th pair or something.
Comment · 1 month ago
I measured this on my past claude code sessions. I have a dataset with full LLM requests and responses and I ended up to an estimated 5-7% savings on tokens. Also with my primarily Opus 4.8 usage, only 5.9% of unique reads even qualify for the bulk-read operation and 58% of the reads were already targeted.
Comment · 2 months ago
Thanks, I however have just one DGX.
Comment · 2 months ago
Any DGX Spark users in this thread? What's your favourite model to run on it?
Comment · 2 months ago
Because everybody has the same system prompt, the KV caching will make this a non-issue. The only cost is the reduced max context length.
Comment · 2 months ago
How do you like the AMOLED screen? I have a Fenix 6, which has the old screen. While it doesn't have a flashlight, I'm very happy with the ability to toggle the backlight on with a single button, which is more than enough for me to see in the dark where I'm going.

I feel that I'm lucky as my Fenix 6 still works as I would not want to switch to an AMOLED screen, which draws too much power to be kept on 24/7.

Comment · 2 months ago
How would you compare it to Opus?
Comment · 3 months ago
That's so cool. I also thought a bit what it would mean to monetise the checklist/packing list app, but I just don't see much business case with it, with all the QA and support requirements.
Comment · 3 months ago
Curious, what have you built? I just wibe coded a packing/checklist app, a llm-powered meal planner and a very specialised app for tracking LAN party network building.
Comment · 4 months ago
Have we reached the capability of a local STT+LLM system being constantly listening for normal speech in a room and being able to understand when the human is addressing the system instead of talking to another human?
Comment · 4 months ago
This! When you have the pictures on your disk just use immich-go to import them.
Comment · 4 months ago
Great article! After reading I started to think there must be some purchable items which would demonstrate colours outside P3 colorspace. It would be cool to hold one on your hand and experience how a photo of it just cannot do justice.

Anybody know any links to webshops for such items?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton