AI

Feeds to Scour
SubscribedAll
Scoured 49 posts in 7.4 ms

ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.

 Longevity  Content type: Code
github.com··Hacker News

An announcement from the Steering Council regarding the JIT project

 🦾Robotics

AgentCompile: An LLM-Guided Compiler for Direct CUDA Inference

 🧫Synthetic Biology  Content type: Academic
arxiv.org·

Forgis-Labs/HEPA: HEPA: Self-supervised horizon-conditioned event predictive architecture for time series. Spotlight at FMSD @ ICML 2026.

 🧠Neuroscience  Content type: Code
github.com··Hacker News

vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

 🦾Robotics  Content type: Academic
arxiv.org·

Show HN: Magenta Real-Time Music Generation on iPhone, Without the GPU

 🧬Genetics  Content type: Code
github.com··Hacker News

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels

 🧠Neuroscience  Content type: Academic
arxiv.org·

Release TorchCodec 0.14: HDR Video Decoding for CPU & CUDA, and Fast Wav Decoder · meta-pytorch/torchcodec

 Wearables  Content type: Code
github.com··Hacker News

A Unifying Lens on Reward Uncertainty in RLHF

 Longevity  Content type: Academic
arxiv.org·

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

 🧠Neuroscience  Content type: Code
github.com··Hacker News

A Regret Minimization Framework on Preference Learning in Large Language Models

 ⚖️Ethics  Content type: Academic
arxiv.org·

KJLdefeated/RL.cu: RLVR training for LLM in CUDA/C++

 🦾Robotics  Content type: Code
github.com··Hacker News

Reinforcement Learning for Flow-Matching Policies with Density Transport

 🔌BCI  Content type: Academic
arxiv.org·

princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how AI actually works

 🦾Robotics  Content type: Code
github.com··Hacker News

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

 ⚖️Ethics  Content type: Academic
arxiv.org·

Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

 🔌BCI  Content type: Academic
arxiv.org·

apple/coreai-models: Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

 🧬Genetics  Content type: Code
github.com··Hacker News

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

 ⚖️Ethics  Content type: Academic
arxiv.org·

Nvidia DGX Spark GB10 – AI Models and Guide with vLLM and Autonomous Script

 💊Pharmacology  Content type: Code
github.com··Hacker News

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

 🧫Synthetic Biology  Content type: Academic
arxiv.org··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