🧠 AI Research - pwadstrom · Scour

Show HN: The Deterministic Core Architecture for AI-Augmented Applications

🎮Reinforcement Learning

brandonbellsystems.com··Hacker News

Less-relevant results

Growing Pains of Starting a Secret Society

🪙cryptocurrency Blog

mrmarket.bearblog.dev··Hacker News

Tracing Eval-Awareness Emergence Through Training of OLMo 3

✍️Prompt Engineering

lesswrong.com·

How to Train Your Goblin

✍️Prompt Engineering

goblins.mchen.workers.dev··Hacker News, Hacker News

Best explanations of how LLMs work

⚙️AI Infrastructure Blog

vorushin.github.io··Hacker News

vishal-dehurdle/state-harness: Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

🧠Claude Code

github.com··Hacker News

Issue 654

🔄Data Engineering Blog

datascienceweekly.substack.com··Substack

Bumblebees can spontaneously solve problems, study finds

🎮Reinforcement Learning

arstechnica.com·

The Effective Sample Size

🎮Reinforcement Learning

alex.smola.org··Hacker News

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.

🧠Machine Learning Code

github.com··Hacker News

I got so mad at poke(rogue)like that I trained a RL agent to beat it for me

🎮Reinforcement Learning Blog

blog.thiagolira.com.br··Hacker News

Meta's smart glasses companion app ships a complete, dormant face-recognition pipeline on a stock account.

🧮Embedding Models

buchodi.com··Hacker News

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

🧠Machine Learning Code

github.com··Hacker News

Two More Methods for Consistency Training and Some New Ways to Apply It

✍️Prompt Engineering

lesswrong.com·

gaelazzo/python_chess: Chess trainer

🎮Reinforcement Learning Code

github.com··Hacker News

Revisiting GSM-Symbolic: Do 2026 Frontier Models Still Fail at Confounded Grade School Math?

lesswrong.com·

markusheimerl/gpt: A generative pretrained transformer implementation

✍️Prompt Engineering Code

github.com··Hacker News

Rohin Shah on AGI Safety

🎮Reinforcement Learning

lesswrong.com·

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

🧠Machine Learning Code

github.com··Hacker News

Optimisation over non-stationary distributions creates weirder minds

🎮Reinforcement Learning

lesswrong.com·

No more posts from pwadstrom's subscribed feeds.

Scour all 25258 feeds Learn more about Feeds

Sign up or log in to see more results

Log in to enable infinite scrolling