Recent submissions

Comment · 2 months ago
Hold onto your butts
Comment · 2 months ago
Don't forget that it actively spies on the user! Say no to telemetry.
Comment · 2 months ago
yikes, no thanks.
Comment · 2 months ago
happy to report my bots have no trouble with anubis or any other pow mechanism, little bit of deno and i'm right through.
Comment · 2 months ago
Thanks for bringing up a service like this, it's quite important. A few serious questions if you don't mind.

Confidentiality? Do you use any sort of logging and if not do you have a way to guarantee that your hosting providers are not snooping?

Price vs Vast or Runpod? If i have a very large or a very small workload do you have a competitive rate vs a gpu provider that offers private gpu access?

Subscription vs Api costs? Do you only offer api rate or will you offer discounted tokens for subscription? Subscription friendly towards open source harnesses such as omp?

Heretic ablation vs other methods? KL divergence scores? Do you post train the weights yourselves or do you offer weights trained by other organizations and is this information available on the service?

Cache hit/miss pricing policy? 90/10 or a different cache pricing policy, and how long do conversions stay in kv cache?

Quantized cache and model? Do you offer a choice if i want a quantized model for speed or a quantized cache? If not do you publish the information?

SGlang vs vllm or other inference engine? Do you publish your engine stack details?

Thank you kindly I find the competition in this space very lacking.

Comment · 3 months ago
As an american i'm quite certain the Australian national dish is made with marmite as opposed to the misconception that kangaroo is unseasoned
Comment · 4 months ago
this is incorrect. you can have multiple clients using screen -x instead of screen -a
Comment · 4 months ago
i honestly don't get why people think ghostty is fast. the gpu acceleration slows it down. maybe i push my machines harder than other people but when the machine is under load either gpu or cpu ghostty starts lagging super hard vs iterm. i've never had a problem with iterm render speed, but iterm never starts lagging when my box is fully maxed out and ghostty does regularly. i try it every few years and ive never seen any improvement.
Comment · 4 months ago
even the market understands this is a massive failure by apple, nobody needs another chat application especially using that stupid overlay window. looks like apple won't leapfrog anyone and has zero agentic features to show and no resetting a password doesn't count as agentic apple.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton