LLMs

Feeds to Scour
SubscribedAll
Scoured 951 posts in 9.6 ms

Google's new open-weights model brings image-generation tricks to AI text generation

 🤖AI Engineering  Content type: News

LLM are universal simulators

 🛡️AI Safety

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

 🤝AI Agents  Content type: Discussion

DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200

 🤖AI Engineering  Content type: News

Franklin Templeton, BNP Paribas see tokenization boosting EU's capital efficiency

 🖥️Backend Development
cointelegraph.com·

Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis

 🔍RAG  Content type: Academic
arxiv.org·

How LLMs Actually Work: A Friendly Map for Humans • oreoro

 🔍RAG

Making FlashAttention-4 faster for inference

 📐System Design  Content type: Blog
modal.com··Hacker News

TradFi advisors want stablecoins, tokenization over Bitcoin: Bitwise

 📐System Design
cointelegraph.com·

Running Qwen 35B MoE at 450k Context on a Single 32GB GPU

 📐System Design

LLM Cheat Sheet

 🔍RAG  Content type: Blog
drkpxl.bearblog.dev·

TOON: Beyond JSON for LLMs

 🤖AI Engineering  Content type: Blog
towardsai.net·

NVIDIA RTX Pro 6000 Blackwell: 96GB GDDR7 and the End of VRAM Anxiety

 🤖AI Engineering  Content type: Blog
fitservers.com·

Does ChatGPT need a psychiatrist? Similarities between human psychopathology and errors in large language models

 🔍RAG  Content type: Academic
nature.com··Hacker News

My Notes on the Progression from Context to Prompt to Harness engineering in making GPT LLMs Useful: (TUESDAY) MAMLMs

 🤖AI Engineering  Content type: News  Content type: Blog

Show HN: BeamWeaver – LangChain/DeepAgents-style agents and workflows for Elixir

 🤖AI Engineering  Content type: Code

ChatGPT easily bypasses its own guardrails; all LLMs are inherently unsafe

 🛡️AI Safety  Content type: Blog
techzine.eu·

NVIDIA A100 vs RTX 4090 for AI Workloads: The Cost Per FLOP Reality

 📐System Design  Content type: Blog
fitservers.com·

Token4Token — pay-per-token inference on Gnosis + Swarm

 🤖AI Engineering
t4t.eth.link··Hacker News

Latest technical articles & videos.

 🤖AI Engineering
certdepot.net·
Sign up or log in to see more results

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