23d ago
Branko Milanovic, economist: 'There will be no return to neoliberal ideology'
Economist Branko Milanovic discusses neoliberal ideology. Off-topic.
23d ago
Open Source Openrouter – Routatic
Go CLI proxy routing Claude Code requests through multiple LLM providers with automatic model selection and format transformation.
23d ago
Detent: AI agent orchestration with worktrees and serialized merge train
Detent: AI agent orchestration framework using worktrees and serialized merge train patterns.
23d ago
Agent-memory systems admit poisoned facts – a reproducible benchmark
CLAI agent memory system with governance and derivation capabilities outperforms retrieval-first memory in poisoning resistance and multi-hop reasoning.
23d ago
Shiproof: Catch App Store rejections before you submit (free GitHub Action
Free GitHub Action to catch Apple App Store rejection causes before submission using deterministic rules engine.
23d ago
GLM-5.2: Another open-source Chinese AI model has Silicon Valley's attention
GLM-5.2 open-source LLM from China with 1M token context window, designed for coding and agentic workflows.
23d ago
Why round-robin load balancing causes incidents (and 9 alternatives)
Technical deep-dive on load balancing failures and alternatives. Infrastructure topic, not AI-related.
23d ago
You don't need ten agents. You need two tracks
Architecture principle: effective multi-agent systems need two tracks rather than many agents. Limited technical detail.
23d ago
Google I/O 2026 Mobile Playbook: AI Studio, Android CLI, and Antigravity
Google I/O 2026: AI tools for mobile development expanded from code assistance to end-to-end lifecycle delivery with AI Studio and Android CLI.
23d ago
Prediction: A Frontier open-source LLM Will Be Released On 3rd December 2026
Analysis predicting open-source LLM will match frontier capability by Dec 2026. Examines gap closure between open and closed models.
23d ago
Cory Doctorow review – the real price of artificial intelligence
Cory Doctorow book review on AI economics and societal impacts. Opinion-focused, no technical content.
23d ago
Microsoft researcher built goat-powered LLM in Age of Empires II
Clickbait headline about goat-powered LLM in game; no technical content provided.
23d ago
Show HN: I rebuilt Jobs To Be Done on scientific foundations and open-sourced it
Open-source implementation of Jobs To Be Done framework with scientific foundations.
23d ago
Llama-dash – One go-to control plane for local inference
Control plane for managing local LLM inference with unified interface.
23d ago
OctaMem: Auditable memory for AI agents, no vector DB to run
OctaMem provides auditable persistent memory infrastructure for AI agents without requiring vector databases.
23d ago
Show HN: Duckle a drag-and-drop visual pipeline designer
Duckle is open-source ETL/ELT desktop studio with 290+ connectors, AI chat assistant, and DuckDB execution.
23d ago
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
GateMem benchmarks memory governance in multi-principal AI agents, evaluating persistent memory with access boundaries.
23d ago
LLMs do not merely reflect the bias of their training, they police it
Opinion piece on how LLMs enforce biases beyond their training data through active policing mechanisms.
23d ago
A Collection of 30 Open Source Chess Applications
Collection of 30 open source chess applications built for learning programming and chess simultaneously.
23d ago
A 0.5s periodic hitch in my local screen stream turned out to be macOS AWDL
Tapflow runs iOS simulators and Android emulators in browsers without toolchain setup, keeping infrastructure local.
23d ago
Open source AI projects from Banco Santander
Banco Santander AI Lab open-source projects: small models, agents, MLOps, and graph ML for financial services.
23d ago
Show HN: KeyGhost – Keyboard app launcher for macOS
KeyGhost: keyboard-based application launcher for macOS to improve app switching efficiency.
23d ago
Patch the Planet: a Daybreak initiative to support open source maintainers
Patch the Planet initiative pairing AI-assisted security research with expert human review to identify and patch vulnerabilities in open-source software.
23d ago
Founders OS – give your AI client your real business context, self-hosted
FoundersOS: open-source MCP server providing business context (CRM, finances, tasks) to Claude, Cursor, or MCP-compatible AI clients.
23d ago
How to Think About AI Before It's Too Late
Podcast episode: Cory Doctorow discusses AI hype, 'enshittification', and sustainability of AI growth narrative.
23d ago
Vibe-coding niche Mac apps
Personal account of using Antigravity AI tool to build Mac apps in Swift/SwiftUI without native development experience.
23d ago
Show HN: Saar Agentic Orchestration Platform
Saar Nexus: multi-persona agentic orchestration platform with context graph memory for workflow automation.
23d ago
Show HN: Onbalance – privacy-first cashflow planning app got a multiuser update
Onbalance 2.0: privacy-first cashflow planning app with multiuser support and offline-first architecture.
23d ago
GitHub Copilot improves productivity 40%
Article about GitHub Copilot productivity claims (40% improvement) from arXiv framework overview page.
23d ago
Show HN: Prismag – Per-block model routing for the terminal and any IDE
Prismag: per-block LLM model routing for terminal and IDEs. Routes code blocks to different models (Opus, Composer) without context switching.
23d ago
Lessons from Building Evals for Financial AI Agents
Blog post on evaluation methodologies for financial AI agents, discussing practical lessons from building evals in a real-world context.
23d ago
Minia2a – A Marketplace Where AI Agents Earn Money
Marketplace platform where AI agents can earn money. Title only, no substantive content.
23d ago
Safebucket – an open source file sharing platform with pluggable infrastructure
Safebucket: open-source file sharing platform with pluggable infrastructure and cryptographic image signing.
23d ago
Yann LeCun „World Models: Enabling the Next AI Revolution" [video]
Video of Yann LeCun discussing world models for AI advancement. Minimal content provided.
23d ago
Anthropic's Mythos mess just keeps getting more complicated
Political commentary on Trump administration's actions regarding Anthropic and a derivative model called Fable 5.
23d ago
Use AI for reviewing code especially when the diff is huge
Guidance on using AI for code review at scale, emphasizing reviewer role in catching out-of-distribution issues AI might miss.
23d ago
Show HN: Gingerpaw : A voice dictation and agent workspace app
GingerPaw is multi-agent coding workspace for macOS running Claude, Codex, Gemini agents in parallel with on-device voice.
24d ago
Engineering Got Faster. Now the Hard Part Is Deciding What to Build
Article on how coding agents crossed capability threshold enabling faster feature shipping, shifting bottleneck from execution to decision-making.
24d ago
Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models
Reflective Masking enables multi-turn reasoning in Mask Diffusion Models by erasing uncertain tokens and regenerating iteratively.
24d ago
Headroom – The context compression layer for AI agents
Headroom library for AI agents that compresses context (tool outputs, logs, RAG chunks, files) before reaching LLM, reducing tokens by 60-95% with reversible algorithms.
24d ago
SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction
SpatialAvatar-0 generates high-quality 4D head avatars using 3D Gaussian Splatting for telepresence and AR/VR.
24d ago
GLM 5.2 vs. Opus
Head-to-head benchmark comparing GLM-5.2 open model against Claude Opus 4.8 on WebGL 3D platformer generation task.
24d ago
Show HN: Posting Machine – two of us running LinkedIn for 20 B2B founders
B2B LinkedIn account automation tool using AI to manage 20 accounts, find target customers, and generate engagement.
24d ago
Bain tests software takeover targets by vibecoding AI replicas
Paywalled Financial Times article behind subscription wall, content not accessible.
24d ago
Ask HN: How are you securing write-enabled AI agents against payload smuggling?
Hacker News discussion about securing write-enabled AI agents against payload smuggling attacks using reality kernel simulation.
24d ago
Show HN: Generate images from the CLI with a ChatGPT subscription (no API key)
Open source Python CLI tool to generate images using ChatGPT subscription without API key, works on free tier, includes AI agent skill integration.
24d ago
Fine-Tuning and Deploying LLMs on Mobile:F/b to learnings
Stub article about fine-tuning and deploying LLMs on mobile devices with learnings documented.
24d ago
Free Agentic AI Webinar: From Agent Design to Production
Webinar announcement on AI agent design and production. Promotional content with no technical details provided.
24d ago
An AI Agent Emailed Me
Stub article with only title, likely personal account of receiving email from AI agent.
24d ago
The AI architecture "attention" can't hold attention
Research study revealing weakness in LLM attention mechanisms compared to human attention using classical psychology test, tests GPT-5, Claude, Gemini.