LLMs

Feeds to Scour
SubscribedAll
Scoured 373 posts in 10.5 ms

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

local llm on laptop 780M GPU using llama + gemma 4 qat

 LLM Inference  Content type: Blog
alper.bearblog.dev·

Orchestrate your LLM pipeline. Locally

 ✍️Prompt Engineering
llmforge.app··Hacker News

How ChatGPT Actually Works (Beginner Friendly)

 ✍️Prompt Engineering  Content type: Blog
medium.com
·

How LLMs are Actually Trained

 🤖AI  Content type: News  Content type: Blog
blog.algomaster.io·

massimo92/spark: CLI tool for serving LLMs with vLLM on NVIDIA DGX Spark. One file, zero friction.

 LLM Inference  Content type: Code
github.com··Hacker News

Why LLMs (still) lack taste

 ✍️Prompt Engineering

Making a Vintage LLM from Scratch

 🧮Vector Databases
crlf.link··Hacker News

Get officially certified in Claude AI for just $19.99

 ✍️Prompt Engineering
pcworld.com·

Claude AI is having a moment — this $20 course helps you keep up

 ✍️Prompt Engineering
boingboing.net·

A free diagnostic for the Claude Certified Architect exam

 ✍️Prompt Engineering  Content type: Discussion  Content type: Tutorial

How J.A.R.V.I.S. Became the Smartest Mind on Earth — What is an LLM?

 ✍️Prompt Engineering  Content type: Blog
medium.com·

Ask HN: Any Local LLM can I run without GPU for Local Agentic workflow AI?

 LLM Inference  Content type: Discussion

#070 - Anthropic walks back Fable 5's throttle, Claude Desktop hides a 1.8GB VM, HTML doubles signups

 📈Performance Engineering
indiehacker.news·

6. Air-Gapped Claude Code - The Claude Code SRE Handbook

 ✍️Prompt Engineering
har-ki.github.io··Hacker News

What Are Tokens in LLMs?

 ✍️Prompt Engineering  Content type: Blog

Slack bot for the whole team, not per-seat

 ✍️Prompt Engineering  Content type: Discussion
plugand.ai··Hacker News

Two old GPUs I salvaged are doing more AI work than a brand new $2000 card, and I won't be upgrading anytime soon

 ✍️Prompt Engineering
xda-developers.com·

Intelligent inference scheduling with llm-d on Red Hat AI

 ✍️Prompt Engineering

high-performance classification API (beats GPT-5.4-mini)

 ✍️Prompt Engineering  Content type: Discussion
classer.ai··Hacker News

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help