News for hackers. Stuff that matters.

droidjj

droidjj on Hacker News

Show HN: HakTok – TikTok for Hacker News

Posted by droidjj on Monday November 02, 2026 @08:47AM
from the show-hn dept.

https://haktok.party

I vibe coded my favorite time-wasting site to look like my wife’s favorite time-wasting site.I’ve had a lot of fun discovering old posts with this. It builds a profile (saved in your browser, not sent to the server) and guesses your interests based on how you interact with each post. Then you get a mix of content that’s roughly 20% current and popular posts, 20% exploratory posts far from your...

( Read More... | 2 comments | 2 points | on HN )
Re:Geist Serif on Friday October 30, 2026 @12:09PM (#50305951)
Sad that “crafted by hand” immediately makes me think Claude made it.
Re:LLM Voice on Thursday October 29, 2026 @05:07PM (#50296000)
Late to this party, but wanted to share my favorite piece of writing about how annoying AI-generated prose it to read: https://storage.courtlistener.com/recap/gov.uscourts.med.612....
Re:MacBook Pro with PROLED XDR Display and Touch on Wednesday October 28, 2026 @01:27PM (#50277317)
I used to work regularly on a commuter train with a firm-provided touchscreen ThinkPad. The touchscreen was great on the train because it was faster (for many things) than reaching for the trackpad. And when you're in a sort of cramped sitting position, reaching forward feels natural.

I'm a lawyer by trade and am forced to lean on GUIs with little keyboard-control support. When I code (for pleasure), I don't miss the touchscreen, but I often miss it when I'm trying to read PDFs and Word documents on the go.

Re:Gemini 4 Carbon on Wednesday October 28, 2026 @01:17PM (#50277075)
I'm assuming this is a post-train of Argon ("Building on Gemini 4 Argon, which was launched two weeks ago, Carbon illustrates the pace at which we’re pushing the frontier forward."), but does anyone know for sure? The post isn't clear.
Re:DeepSeek just open-sourced its inference engine on Tuesday October 20, 2026 @12:39PM (#50169043)
I assume weights can also be IP in the form of trade secrets.
Re:Janas: Run LLMs larger than RAM by streaming experts from SSD on Monday October 12, 2026 @09:42PM (#50065514)
Based on how vibe-coded this whole thing is, I’m guessing the newer models weren’t in the training data and the agent just picked what it knew existed.
Re:GLM-Legal: Advancing Agentic Legal Intelligence on Monday October 12, 2026 @07:04PM (#50064297)
There’s a whole niche of legal scholarship around this idea (and some startups): https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5331811
Re:Muse Wonder on Monday October 12, 2026 @01:44PM (#50060009)
Pricing is available here: https://dev.meta.ai/models/muse-wonder

Input -- $4.00

Cached input -- $0.20

Output -- $20.00

Edit: Upon closer inspection, the benchmark scores for "Muse Wonder" on the main marketing page are actually for "Muse Wonder Full," which is only available on the higher-tier subscription plans. This pricing is for "Muse Wonder."

Re:Muse Wonder on Monday October 12, 2026 @01:42PM (#50059973)
> Zuck is proven once again as a great executioner
Re:Computers Cannot Make Decisions on Saturday October 10, 2026 @10:27AM (#50033369)
If computers can’t make decisions, can humans? Relevant: https://plato.stanford.edu/entries/computational-mind/

edit: This wasn’t meant to be a rhetorical question!

Re:Python 3.15.0 on Friday October 09, 2026 @11:12AM (#50021644)
> The experimental JIT compiler has been significantly upgraded, with 7-8% geometric mean performance improvement on x86-64 Linux over the standard interpreter, and 11-12% speedup on AArch64 macOS over the tail-calling interpreter.

Nice to see improvements here!

Older »