HN bookofjoe 13d ago

Panasonic's new residential CO₂ air-to-water heat pump:coeff of performance=6.1

Heat pump technology article. Off-topic for AI/tech interests.

HN benchtobedside 13d ago

Anthropic launches AI drug discovery program

Brief mention of Anthropic drug discovery program. No technical details or substantive content provided.

HN itsmeduncan 13d ago

Commonplace: Self-hosted, privacy-tiered memory for your AI agents

Self-hosted memory system for AI agents with privacy-tiered architecture for persistent context management.

HN abdelhousni 13d ago

Quran MCP

MCP (Model Context Protocol) implementation for Quran access. Limited detail from title.

HN GPrab 13d ago

Claude Code Skills: 98 AI architectures, Haiku at 93% of Fable 5 quality

Open source repository demonstrating 98 AI architectures using Claude Haiku achieving 93% of Fable 5 quality at 1/125th cost with benchmarks and architecture details.

HN dcriglerd 13d ago

We Built a Tool to Predict Runaway LLM Costs (Before They Kill Your Margins)

Tool for monitoring and predicting LLM API costs to prevent budget overruns in AI products including agents, copilots, and automation platforms.

HN sakuraiben 13d ago

Show HN: TakoVM – open-source sandboxing for your agent's code

TakoVM provides secure sandboxed code execution for AI agents with isolated Docker containers, ephemeral workspaces, job queues, and gVisor support.

HN sudo_cowsay 13d ago

As better chatbots get harder to build, AI turns to simulated worlds

Discussion of simulated worlds for chatbot training. Limited substantive content from headline.

HN smitec 13d ago

Autoresearch, Claude and Constrained Optimization

Project using Claude AI with constrained optimization for automated research tasks, exploring AI productivity claims with evidence.

HN koliev 13d ago

Whenever Alignment Matters

Incomplete article title with no substantive content.

HN abipal15 13d ago

GPU Compute Tightness Index

Metric or index for measuring GPU computational efficiency. Limited context from title.

HN franticstone 13d ago

Show HN: Open-source restreaming and live studio

Self-hosted multistream studio supporting RTMP, SRT, WebRTC ingestion with browser-based production switching and multi-platform fan-out.

HN rbanffy 13d ago

Trump's plan to redesign every .gov website leads to AI-designed horrors

Government website redesign project using AI faces delays. Reports on policy implementation challenges.

HN rafalswietek 13d ago

Show HN: Turning Sentry errors into AI generated GitHub PRs with fixes

AI agent that analyzes Sentry errors and generates GitHub pull requests with fixes. Integrates via OAuth and GitHub App.

HN perseusai 13d ago

Show HN: Mimir – local-first encrypted memory for AI agents (single Rust binary)

Mimir: local-first encrypted memory system for AI agents as single Rust binary. Developer tool for agent state management.

HN alok-g 13d ago

Meta's brain-scanning system reads sentences non-invasively, code open source

Meta releases open source code for non-invasive brain-scanning system that reads sentences. Novel neurotechnology with open source component.

HN danboarder 13d ago

FluidVoice - Open source voice-to-text dictation app for macOS with local AI

Open source macOS voice-to-text dictation tool using local AI models. Practical developer tool for speech recognition.

HN ihariv 13d ago

SilentJSON – A zero-allocation JSON parser for Go (3.4 GB/s)

SilentJSON is a zero-allocation, reflection-free JSON parser for Go achieving 3.4 GB/s throughput without code generation.

HN thanhhaimai 13d ago

Gemini Spark updates: macOS launch, connected apps and more

Google Gemini Spark updates including macOS launch and connected apps integration. Title only, details missing.

HN handfuloflight 13d ago

Bb: The IDE for loop driven development

Bb IDE orchestrates coding agents with CLI for agents, shell scripts, and automation bots integrated into sidebar workflow.

HN vincent_s 13d ago

Claude Code Just Got 5x More Expensive

Price increase announcement for Claude Code API.

HN bhaktatejas922 13d ago

Show HN: Morph Reflexes – Multi-head classifiers for agent traces

Multi-head classifier system for detecting agent failures (looping, reasoning errors) using small LLMs with custom vLLM kernel for production cost and latency efficiency.

HN peterdemin 13d ago

I ported Kubernetes to the browser

Browser-based Kubernetes implementation by ngrok.

HN duarteapereira 13d ago

Periskop – product discovery (MCP/API) for AI agents

Periskop: product discovery MCP/API tool designed for AI agents. Developer tool for agent integration.

HN ValentineC 13d ago

macOS: Code_sign_clone grows unbounded (62 GB+) across Codex auto-updates

macOS Codex app accumulates uncleaned code signing data in temp folders, consuming 62+ GB over time due to frequent auto-updates.

HN Cyrus2050 13d ago

Build, run, and market businesses 24/7 with AI

Leapd platform claims to automate business creation and operation with AI. Marketing pitch, limited technical details.

HN romaniitedomum 13d ago

Prompt Injection as Role Confusion

Analysis of prompt injection attacks framed as role confusion vulnerability in LLMs. Security research on LLM robustness.

HN kage18 13d ago

Show HN: Kage, verification and freshness for Google's OKF agent memory

Kage framework adds verification and freshness checking to Google's Open Knowledge Format (OKF) for agent memory management, ensuring proper memory creation and validation.

HN lucamark 13d ago

Claude Sonnet 5 – benchmark results

Claude Sonnet 5 benchmark results announced. Minimal content with no details provided.

HN m3h 13d ago

GPT 5.5 uses Grug Brained talk during reasoning for 2x token efficiency

Rumor about GPT 5.5 using simplified language during reasoning for token efficiency. Unverified claim with no technical details.

HN gurjeet 13d ago

Why AI Hasn't Cured Anything yet [video]

Video discussing why AI hasn't produced medical breakthroughs. Opinion/commentary without technical depth.

HN jamesblonde 13d ago

We used coding agents to add RonSQL support to RonDB

Case study using coding AI agents to implement RonSQL support in RonDB database. Practical application of AI agents.

HN dphuang2 13d ago

Learning to Replicate Expert Judgment in Financial Tasks

Research on training models to replicate expert judgment in financial tasks using machine learning.

HN decorner 13d ago

OrgForge: The Next Step in Enterprise AI Simulation

OrgForge simulation framework for enterprise AI addressing hallucinations through maintaining boundaries between processes and generated text.

HN supo 13d ago

Show HN: Distributed LLM tracing and GH PR/issue linking [Apache 2.0]

Open-source tracing tool for distributed LLM agents, monitoring token usage and linking to GitHub PRs/issues for development workflow tracking.

HN louwrentius 13d ago

The AI Mirage or Why I Think the Hype Can't Sustain Itself

Opinion article arguing AI hype is unsustainable; speculative content without technical evidence.

HN runningmike 13d ago

Demystifying Security Risks of AI-Powered Applications on Pre-Trained Model Hubs

Security research examining vulnerabilities in AI applications using pre-trained models from model hubs.

HN idontwantthis 13d ago

Is There an Official Maintained Python Koans Repo?

Question about Python Koans, an interactive tutorial for learning Python through test-driven exercises.

HN yeychenne 13d ago

Show HN: Trains – leaderless total-order broadcast in Rust, formally verified

TRAINS is a formally verified leaderless total-order broadcast primitive in Rust for control-plane coordination, alternative to Paxos/Raft.

HN matt_d 13d ago

Accelerating LLM Inference on AMD GPUs with Low-Latency GEMMs

Technical optimization for LLM inference on AMD GPUs using low-latency GEMM implementations.

HN indrora 13d ago

Zluda (CUDA-compatible runtime for AMD) loses funding again, gains 32bit compat

ZLUDA CUDA-compatible runtime for AMD GPUs adds 32-bit compatibility and PhysX/Blender support despite losing funding.

HN dv35z 13d ago

Ask HN: Where did the terminology (AI) "System Card" come from?

HN discussion thread asking about origins of AI terminology like 'system card', 'alignment', and 'safety'.

HN bgubitosa 13d ago

Claude Sonnet 5 Review

Product review of Claude Sonnet 5; mostly navigation and legal boilerplate with minimal substantive content.

HN zkldi 13d ago

Tell HN: Installing Cursor on iOS irreversibly changes your privacy settings

User reports that installing Cursor iOS app irreversibly changes privacy settings, downgrading from legacy 'Do not store code' mode.

HN throwawayamzn1 13d ago

Agentic AI and the End of Static Information

Discussion of agentic AI systems replacing static information retrieval with dynamic autonomous decision-making.

HN jamil20 13d ago

GameBoy Emulator in WASM

Game Boy emulator written in C with SDL3, featuring flat state design and focus on readability.

HN eric_h 13d ago

Embedding Forbidden Text in Spyware to Discourage AI Analysis

Security technique embedding obfuscated text in malware to complicate AI-based analysis and detection.

HN thunderbong 13d ago

Vega: Zero-knowledge proofs for digital identity in the age of AI

Cryptographic identity verification system using zero-knowledge proofs for AI applications.

HN mineti 13d ago

AI coding tools should reach beyond the editor

Opinion on expanding AI coding tools beyond editor integration with minimal detail provided.

HN tanavc 13d ago

Show HN: Makes local LLMs faster and more reliable by optimizing for your device

Tool optimizing local LLM inference with 39% faster time-to-first-token and 46% faster agent execution through adaptive resource management.