LLMs

💬 LLMsSpecific

Large Language Models, GPT, Transformers, Natural Language Processing

Feeds to Scour
SubscribedAll
Scoured 159 posts in 15.5 ms

Claude Mythos Glasswing: Why AI Vuln Discovery Terrifies Me

 🧠LLM  Content type: Blog  Content type: Discussion
tildalice.io·

know the mother tongue of your LLMs

 🤖Transformers
mothertoken.inigoimaz.com··Hacker News

Show HN: Audit any AI/data pairing with Veritrooper

 ✍️Prompt Engineering
veritrooper.com··Hacker News

Report: GKE Inference Gateway delivers up to 92% faster AI responses

 💡AI Reasoning  Content type: Blog
cloud.google.com··Hacker News

Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM

 ⌨️CLI Tools
deemwar-products.github.io··Hacker News

Purpose-built local AI agents

 ✍️Prompt Engineering  Content type: Blog
samihonkonen.com··Hacker News

Building & Benchmarking: LLMs on a 16GB Jetson Orin NX for Hermes Agent

 💾Retro Computing  Content type: Blog
dnhkng.github.io·

Show HN: Ext-Infer

 ⌨️CLI Tools
infer.displace.tech··Hacker News

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

A wild idea: Abstract reality using ontology

 ✍️Prompt Engineering  Content type: Discussion
news.ycombinator.com··Hacker News
Less-relevant results

Re-quantizing a local LLM 14x faster by skipping the tensors that didn't change

 🔥PyTorch  Content type: News  Content type: Blog
andreaborio.substack.com··Substack

Job Searcher

 ✍️Prompt Engineering  Content type: Blog
huggingface.co·

Meet Hades: The malware that lies to AI security agents

 ✍️Prompt Engineering  Content type: News
infoworld.com··Hacker News

Arithmetic Without Numbers – How LLMs Do Math

 ✍️Prompt Engineering
alvaro-videla.com··Hacker News

SafeRun: Enabling Determinism in LLM Planning for Running

 💡AI Reasoning  Content type: Academic
arxiv.org·

Nvidia Nemotron 3 Ultra

 🤖AI
research.nvidia.com··Hacker News

Aspen: Own your intelligence

 ✍️Prompt Engineering  Content type: Discussion  Content type: Tutorial
runonaspen.com··Hacker News

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

 ✍️Prompt Engineering
tenureai.dev··Hacker News, Hacker News

KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

 💾Retro Computing  Content type: Code
github.com··Hacker News

Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required

 ✍️Prompt Engineering  Content type: Blog
aws.amazon.com·

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