LLMs

Feeds to Scour
SubscribedAll
Scoured 944 posts in 12.9 ms

Why Your LLM Gets Dumber With More Context

 🤖AI Engineering
siliconopera.com·

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

 🖥️Backend Development  Content type: Blog

MTG Bench: Testing how well LLMs can play Magic

 🤝AI Agents

Orchestrate your LLM pipeline. Locally

 🤖AI Engineering

Show HN: Ext-Infer

 🔍RAG

A Complete Beginner's Guide to Local LLM Inference

 🔍RAG  Content type: Blog

Comprehensive evaluation of LLM capabilities for interpretation and analysis of genome-scale metabolic models in metabolic engineering

 🤖AI Engineering  Content type: Academic
biorxiv.org·

CommBench: Can LLMs Write Correct and Efficient GPU Communication Code?

 🤖AI Engineering

LangChain Explained: Understanding Models, Prompts, Chains, Memory, Indexes, and Agents

 🤖AI Engineering  Content type: Blog
towardsai.net·

Timing Trick Cuts Energy Used in LLM Training by Up to 14 Percent

 📐System Design  Content type: News

lightmetal: GPU LLM Inference From a Single Java 25 JAR

 🔍RAG  Content type: Blog
adambien.blog·

Show HN: In-browser real LLM token counter and cost estimation

 🖥️Backend Development
holaclaw.ai··Hacker News

A reporting checklist for large language models in behavioural science

 🤝AI Agents  Content type: Academic
nature.com·

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

 🛡️AI Safety
xda-developers.com·

harmansingh4163-ai/ESP-32-s3-Story-maker-LLM: 15M/42M-param Llama split across two ESP32-S3s over 3 wires — too big for either chip alone. INT4, flash mmap, bit-exact verified.

 📐System Design  Content type: Code
github.com··Hacker News

Prompt Caching Explained: The AI Concept That Can Save Millions of Tokens

 🔌API Design  Content type: Blog

Research Proposal: Decoupled RISC-LLM Architectures via Circadian Synaptic Consolidation

 📐System Design
aermia.com··Hacker News

A Plea to the Labs: Let the Models Diagnose.

 🛡️AI Safety  Content type: Blog

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

 🤖AI Engineering  Content type: News

Why LLMs (still) lack taste

 📐System Design

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