Michael Kohn - tin can phone modem
mikekohn.net·1d
🧪Cassette Hacks
ChatGPT and other AI models can be ‘poisoned’ to spew gibberish, researchers warn
the-independent.com·1d
🔓Hacking
Sentient Config is a Code Smell
assertnotmagic.com·19h
🔄Language Evolution
Dev Services for Spring Boot Using Arconia
thomasvitale.com·9h·
Discuss: Hacker News
🔌Archive APIs
7x faster JSON in SQL: a deep dive into Variant data type
e6data.com·10h·
Discuss: Hacker News
📋DFDL
Can AI Co-Design Distributed Systems? Scaling from 1 GPU to 1k
harvard-edge.github.io·1d·
Discuss: Hacker News
🎯Performance Proofs
Building the Reasoning Engine at Axiom
axiommath.ai·1d·
Discuss: Hacker News
⚔️Lean Tactics
Software Architecture Horror Story
blog.mihaisafta.com·18h·
Discuss: Hacker News
🔌Interface Evolution
CaRT: Teaching LLM Agents to Know When They Know Enough
arxiv.org·1d
🔲Cellular Automata
Dynamic Power Allocation for High-Bandwidth USB-C Alt Mode Displays using Reinforcement Learning
dev.to·7h·
Discuss: DEV
🎯Emulator Accuracy
Building a Streaming Data Pipeline with Kafka and Spark: Real-Time Analytics Implementation Guide
dev.to·1d·
Discuss: DEV
🌊Apache Kafka
AgentAsk: Multi-Agent Systems Need to Ask
arxiv.org·1d
🧮Kolmogorov Complexity
Node.js vs Go in Practice: Performance Comparison of chaos-proxy and chaos-proxy-go
dev.to·4h·
Discuss: DEV
⚡gRPC
Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
arxiv.org·3d
🧠Machine Learning
Chronological Thinking in Full-Duplex Spoken Dialogue Language Models
arxiv.org·3d
⏱️Interval Parsing
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.org·1d
⚡Proof Automation
From Documents to Dialogue: A step-by-step RAG Journey
dev.to·1d·
Discuss: DEV
📊Multi-vector RAG
Tutorial: Build ChatGPT App Todo App
github.com·9h·
Discuss: Hacker News
⚡gRPC
Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection
arxiv.org·1d
🤖Grammar Induction
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
arxiv.org·2d
💻Local LLMs