Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
jadbox's comments
login
jadbox
9 hours ago
|
parent
|
context
|
next
[–]
| on:
From Supabase to Clerk to Better Auth
I feel seen. It's compounded if you also need to add HIPAA row-level security compliance that spans to every form of resource.
reply
jadbox
1 day ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Google Chrome silently installs a 4 GB AI model on...
I believe webpages that use the API must request from the user via a system permissions dialogue to aces the prompt API, according the docs a few months ago.
reply
scriptsmith
1 day ago
|
parent
|
next
[–]
It can only be called after the user has interacted with the page, but there's no dialogue from the browser
https://developer.chrome.com/docs/ai/get-started#user-activa...
reply
jadbox
1 day ago
|
parent
|
context
|
prev
|
next
[–]
| on:
GLM-5V-Turbo: Toward a Native Foundation Model for...
What version of Kimi was that using? Do you have any specific insight on Kimi vs GLM in real world scenarios?
reply
_pdp_
1 day ago
|
parent
|
next
[–]
K2.6. My experience is anecdotal but GLM was able to complete the task more throughly and quicker.
reply
jadbox
1 day ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Zig → Rust porting guide
I'm very curious what Zig vs Rust code looks like for the same project! What are your thoughts so far?
reply
jadbox
4 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Grok 4.3
I get great results when operating at just a 'file' level. It's not so great at editing across many files.
reply
jadbox
6 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
U.S. Senators Vote to Ban Themselves from Trading ...
Note that this is just a code of conduct change for the ethics committee, not a law. Something is better than nothing.
reply
jadbox
7 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Show HN: A new benchmark for testing LLMs for dete...
Wow, Qwen3.5-35B is absolutely punching above its weight. Perhaps it's the best/cheapest model for just JSON operations?
reply
khurdula
6 days ago
|
parent
|
next
[–]
We do love Qwen! It can be an easy choice when confused looking at this leaderboard.
reply
jadbox
8 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Ghostty is leaving GitHub
What OSS friendly platform will you be moving to?
reply
jadbox
9 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
GitHub Copilot is moving to usage-based billing
Dang, Gemini 3 Pro also jumped: 1->6
reply
jadbox
9 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Microsoft and OpenAI end their exclusive and reven...
Deepseek v4, Qwen 3.6 Plus/Max, GLM 5+ are all pretty solid for most work.
reply
sexy_seedbox
9 days ago
|
parent
|
next
[–]
Don't forget the Kimi 2.6 as well!
reply
More
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
reply