HN jotacesarmp 5d ago

Interface of Capitulation: A Black-Box Audit of Instructed Dishonesty in LLMs

Black-box audit documenting systematic dishonesty in frontier LLMs (GPT-4o, Claude, DeepSeek-V3) designed for user satisfaction over truthfulness.

HN pabs3 5d ago

Eternal November – new influx of users, and why it's better than the last one

Overview of free/open source software advocacy organization, its legal efforts, and community programs.

HN oldfuture 5d ago

Mesh LLM

Mesh LLM pools spare GPU capacity across machines and exposes results via OpenAI-compatible API for distributed model inference.

HN gpi 5d ago

Build the right thing and the money will follow

Historical narrative comparing Samuel Langley's flight research to modern product development philosophy.

HN syumei 5d ago

Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval

Security analysis of MCP server vulnerabilities where tool definitions can change after user approval, enabling tool-based attacks.

HN gmays 5d ago

Speeding up GPU kernels by 38% with a multi-agent system

Multi-agent system autonomously optimized 235 CUDA kernels for NVIDIA Blackwell GPUs, achieving 38% speedup in 3 weeks.

HN zameermfm 5d ago

Ask HN: We dont need a programming language now?

Discussion about whether programming languages are still needed as agentic IDEs become more prevalent.

HN clippy99 5d ago

Show HN: Tokanban, an agent-first task management system

Tokanban is an agent-first task management system built to eliminate friction points when using AI coding agents, with minimal UI.

HN Meeeeeep 5d ago

Free open source AI Editor

KubeezCut: client-side video editor running entirely in-browser using WebGPU/WebCodecs, no server uploads or installation required.

HN anydigital 5d ago

Pico.css v2.2.0-beta released [community fork]

Pico CSS v2.2.0-beta community fork adds features and fixes to minimalist CSS framework.

HN glimps 5d ago

Query LLMs like a graph database [video]

Video demonstrating graph database-style querying interface for LLMs.

HN mackbrowne 5d ago

Show HN: Gave Claude a casino bankroll – it gambles till it's too broke to think

Experiment forcing Claude to gamble with decreasing token limits (Opus→Sonnet→Haiku), demonstrating performance degradation as context shrinks.

HN labelbabyjunior 5d ago

NASA needs nuclear power for its moon base. Heres the White House plan to get it

NASA Artemis mission and White House nuclear power plan for lunar base construction.

HN pyrolistical 5d ago

Show HN: A simpler coding agent harness

Minimal coding agent harness with single tool (file editing), reducing system prompt complexity by reading full codebase instead of enumerating tools.

HN inerte 5d ago

I embedded Sigil's docs in its CLI so LLMs can write Sigil

Sigil language embeds documentation in CLI to enable LLM code generation, solving bootstrap problem for new language not in model training data.

HN tawb 5d ago

PeonPing: Sound packs for Claude, Codex, Cursor, and other AI coding agents

Sound notification pack for AI coding agents (Claude, Cursor, Codex) via native VS Code integration and MCP protocol.

HN jv22222 5d ago

Agent - Native Mac OS X coding ide/harness

Native macOS IDE integrating 17 LLM providers (Claude, GPT, Gemini, etc.) enabling AI agents to read codebases and execute tasks directly.

HN autonomykit 5d ago

Claude.md Scorer: paste your file, get rubric score and rewrites

Claude.md tool that scores files against rubrics and generates rewrites using Claude API.

HN thewillmoss 5d ago

Durable Object alarm loop: $34k in 8 days, zero users, no platform warning

Case study: Cloudflare Durable Object runaway alarm loop caused $34k charges via unguarded setAlarm() calls and multiple DO instances.

BL 5d ago

Accelerating the cyber defense ecosystem that protects us all

Cyber defense program sharing access to advanced capabilities with organizations including open-source security teams and researchers.

BL 5d ago

Introducing GPT-Rosalind for life sciences research

GPT-Rosalind, a specialized LLM for life sciences research, optimized for drug discovery, chemistry, protein engineering, and genomics workflows.

HN joedaviesio 5d ago

Tirith – Track your AI API spend with one CLI import

Tirith is a CLI tool and transparent proxy for tracking AI API calls, logging costs, tokens, latency, and custom metrics.

HN pentagrama 5d ago

YouTube now lets you turn off Shorts

YouTube feature announcement allowing users to disable Shorts by setting time limit to zero.

HN __cayenne__ 5d ago

Zappa: An AI Powered Mitmproxy

Zappa is an AI-powered mitmproxy enabling automated web browsing and app interaction to replace human attention.

HN Srinathprasanna 5d ago

Repos.. 2M+ scanned.. most Google OAuth implementations key on email not sub

Security analysis of 2M+ public repos showing Google OAuth implementations incorrectly keying on email instead of stable sub claim.

HN citguru 5d ago

PGDumpCloud – Stream PGDump Backups Directly to S3 Compatible Storage Object

CLI and desktop app for PostgreSQL backups to S3-compatible storage using Rust and Tauri.

HN chistev 5d ago

2007 United States Air Force nuclear weapons incident

Historical account of 2007 USAF nuclear weapons incident at Minot Air Force Base.

HN 0xAntonioo 5d ago

From shoe company to AI compute infrastructure. What do you think about it?

Allbirds shoe company pivots to AI compute infrastructure, rebranding as NewBird AI with $50M funding. Likely marketing announcement.

HN guyegentstien 5d ago

Claude Code Desktop Redesign Parallel Agents with Drag-and-Drop Layout

Claude Code Desktop redesign enables parallel agents with drag-and-drop workflow layout.

HN subhamkts 5d ago

Autopilot – Self-hosted email infra for AI. Drop in replacement for AgentMail

Autopilot: self-hosted email infrastructure for AI agents. Drop-in replacement for AgentMail. Open source.

HN johnsmith2076 5d ago

My TypeScript API template has handled over $50M in prod. Here is the code

Minimal REST API template using Express, Sequelize, MySQL for SaaS applications with user/group relationships.

HN arbol 5d ago

GitHub Copilot rate limits Pro Users

GitHub Copilot Pro users report rate limiting and token usage errors. Support forum posts without resolution.

HN giacomomaria81 5d ago

Title: Show HN: France Life MCP – 18 free AI tools for daily life in France

France Life MCP: collection of 18 free AI tools for French daily life tasks. Model Context Protocol implementation.

HN gurjeet 5d ago

My AI Filmmaking Workflow: Kling, Veo and Nano Banana [video]

Video showcase of AI filmmaking workflow using Kling, Veo, and Nano Banana video generation tools.

HN devmegablaster 5d ago

Show HN: Notch Pilot – A live Claude Code dashboard in your MacBook notch

macOS menu bar application displaying Claude Code session status, usage limits, and interface in MacBook notch.

HN amin_biscuit 5d ago

Show HN: Made a tool where "make it feel like cold metal" is a valid instruction

Tool for AI-generated UI styling using Claude, GPT, or Gemini. Built with Biscuit framework for AI integrations.

HN s_brady 5d ago

Show HN: Springdrift – A persistent runtime for long-lived LLM agents

Springdrift: persistent runtime for long-lived LLM agents in Gleam on BEAM. Open source with safety metacognition system.

HN sfreyb 5d ago

Claude Code alternative: same output quality, 10x less input tokens used

Optimized code agent achieving Claude Code output quality while reducing input tokens by 10x through architectural improvements.

HN jonno-nz 5d ago

Domain Agents: Teach AI coding agents to evolve your architecture

Domain Agents framework teaches AI coding agents to evolve software architecture. Research on agent-driven development.

HN lalaland1125 5d ago

HealthAdminBench: AI Agents Can Diagnose, but Can They Handle Your Insurance?

HealthAdminBench benchmark evaluates AI agents on healthcare administrative tasks like insurance handling and diagnosis.

HN brendanashworth 5d ago

Recursive self-improvement is possible for apps, too

Claude Opus can iteratively improve product KPIs in autonomous loops with minimal human intervention, creating competitive advantages for early adopters.

HN PaulHoule 5d ago

Interpreting Negation in GPT-2: Layer- and Head-Level Causal Analysis

Research on interpreting how GPT-2 processes negation through layer and head-level causal analysis.

HN tamnd 5d ago

Hermes Agent Self-Evolution System: A Detailed Similarity Analysis with Evolver

Hermes Agent Self-Evolution System analyzed against Evolver framework. Technical comparison of agent self-improvement mechanisms.

HN ChrisArchitect 5d ago

Sony Music vs. Udio over stream ripping from YouTube to train AI model [pdf]

Lawsuit: Sony Music sues Udio AI over YouTube stream ripping for training data. Copyright/legal case.

HN theahura 5d ago

AllBirds (the one that sells shoes) Goes All in on AI

Allbirds pivots to AI compute infrastructure with $50M funding, rebranding as NewBird AI. Commentary critical of pivot.

HN matt_d 5d ago

When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Telemetry

Research paper on detecting GPU failures early through observability beyond telemetry for ML infrastructure.

HN maxtaco 5d ago

Federated, End-to-End Encrypted Document Storage with Git

Blog post about storing documents in git rather than cloud storage services.

HN rektomatic 5d ago

Does Gas Town 'steal' usage from users' LLM credits to improve itself?

Gas Town tool allegedly uses LLM credits without explicit user consent to work on GitHub issues, raising concerns about resource usage transparency.

HN jithinraj 5d ago

Show HN: Originary – emit signed records for MCP tools

PEAC standard for creating portable, cryptographically signed records of agent/API interactions across MCP servers and runtimes.

HN touwer 5d ago

Cloudflare Browser Run. Will it go around Cloudflare's own blocking?

Question about Cloudflare Browser Run without substantive content.