HN V1kingLightning 23d ago

I designed an AI fact-checker agent (Turing). To prevent hallucinations [video]

Video about an AI fact-checker agent designed to prevent hallucinations; lacks detailed technical information.

HN AaronO 23d ago

OpenAI DayBreak – GPT-5.5-Cyber

OpenAI Daybreak tool for automated vulnerability discovery and patch generation in software systems.

HN ilreb 23d ago

Home Assistant OS 18.0

Home Assistant OS 18.0 release with Linux kernel and Docker updates across platforms.

HN joeyhage 23d ago

AWS introduces Lambda MicroVMs: isolated sandboxes with full lifecycle control

AWS Lambda MicroVMs enable isolated execution of user/AI-generated code with VM isolation and stateless control.

HN nreece 23d ago

Universal basic income, the utopian idea resurging in Silicon Valley

Opinion piece on universal basic income trend in Silicon Valley.

HN maxloh 23d ago

Palmier Pro: macOS video editor built for AI

Open source macOS video editor integrating AI agents for collaborative video generation and editing.

HN yshunnar 23d ago

Show HN: DELN – An interactive atlas of AI training datasets

GLM-5.2 evaluated on AA-Briefcase benchmark for agentic knowledge work with multi-week realistic projects.

HN sgallant 23d ago

Why Are LLMs Smart?

API implementation achieving 280 tokens per second for GLM-5.2 model.

BL 23d ago

How Omio is building the future of conversational travel

Omio uses OpenAI APIs for AI-powered travel booking and trip planning, reducing development time from quarters to months.

HN lumpa 23d ago

Porting Moebius 0.2B image inpainting model to run in browser with Claude Code

Guide on porting Moebius image inpainting model to run in web browser using Claude Code.

HN sharva 23d ago

What it takes to get high Text-to-SQL accuracy in production

Techniques and strategies for achieving high accuracy in Text-to-SQL systems used in production environments.

HN 882542F3884314B 23d ago

Sakana Fugu multi-agent system delivered as one model

Sakana Fugu: multi-agent system delivered as single model, dynamically orchestrates models for complex tasks via API.

HN tortilla 23d ago

The Technium: Why Are LLMs Smart?

Article on why large language models are capable and intelligent.

HN declanjackson 23d ago

GLM-5.2 is above GPT-5.5 in new agentic knowledge work eval

Commentary on decline of traditional prestige career paths.

HN skogstokig 23d ago

Server Survival

Interactive 3D game simulating cloud architecture scaling with DDoS attacks and budget management.

HN modinfo 23d ago

Knowledge Catalog – universal context engine for agents

Google Knowledge Catalog: AI data catalog with knowledge graph providing context and metadata management for AI agents.

HN bjourne 23d ago

Ask HN: How do you make the LLM generate good code?

Discussion on techniques for getting LLMs to generate higher quality code for specific tasks.

LB tvm.apache.org via sanxiyn 23d ago

TIRx: An Open Compiler Stack for Evolving Frontier ML Kernels

TIRx open-source compiler for ML kernels supporting GPU and AI accelerators, handling agent-generated code.

HN indynz 23d ago

PsychAdapter: Personality in LLM output via trait-language patterns, not prompts

PsychAdapter: transformer architecture using trait-language patterns to reflect personality and mental health in LLM outputs.

HN dewey 23d ago

Bohemia Interactive: Cold War Assault Remastered Source Code on GitHub

Game engine source code from 2001 released on GitHub, modernized to C++20 with cross-platform support.

HN simonpure 23d ago

Software Engineers Face an AI 'Identity Crisis,' VC Partner Says

Opinion piece on software engineers' role concerns in the AI era.

HN petethomas 23d ago

Meta pauses AI training program tracking employee keystrokes after internal leak

Meta paused internal AI training program after data leak exposed employee conversations and performance data across company.

HN tmakatos 23d ago

Show HN: Device emulation outside QEMU using vfio-user and libvfio-user

vfio-user protocol enables device emulation in separate process outside QEMU. Allows flexible implementations like SPDK for multi-VM disk handling.

HN vtorosyan 23d ago

There Is Too Much

Engineer reflects on workplace stress from code generation and rapid development pace, loss of learning and enjoyment.

HN birdculture 23d ago

Lines or Less: Test Case Minimization

Property-based testing library implementing test case minimization in minimal code.

HN polskibus 23d ago

Sakana AI Ships Fugu, an Orchestration Model Claiming Fable 5 Performance

Sakana AI releases Fugu orchestration model achieving performance comparable to Fable 5.

HN steviee 23d ago

Show HN: Git Issues – versioned task management for AI agents

Version control task management system designed for AI agent workflows.

HN polskibus 23d ago

Japan's 'Sakana Fugu' multiagent AI scores well against Fable 5, GPT 5.5

Sakana AI's Fugu multiagent model demonstrates competitive performance against Fable 5 and GPT 5.5.

HN PaybackTony 23d ago

Show HN: Localish – Your Localhost in the Cloud

Cloud hosting service for React/HTML apps with AI generation features.

HN boramdd 23d ago

The comment paradox: clean code in age of AI agents

Technical discussion on code comments as implicit prompts for AI coding assistants.

HN kvasserman 23d ago

Show HN: Hybrid search of 540K+ US Government datasets on 2 CPU cores. No LLMs

Search system for 540K+ US government datasets using hybrid search (traditional + semantic) without LLMs. Runs on 2 CPU cores.

HN peterdemin 23d ago

Webernetes – Kubernetes in Browser

Kubernetes simulator running in browser without backend, educational tool for visualization.

HN marceld23 23d ago

Show HN: A 100% AI-generated 3D voxel game I built with my 10yo son

Open-source 3D voxel game entirely AI-generated with documented workflow.

HN ciwolex 23d ago

Ask HN: What are some rock solid open source vector databases

Community question seeking recommendations for open-source vector databases.

HN Ryanaga 23d ago

AI Agent / Harness Engineer

Research on Concept Modulation Models framework addressing identifiability and extrapolation in conditional latent variable models and causal representation learning.

HN pseudolus 23d ago

AI Has Already Killed Academia as We Know It

Academic perspective on how AI has disrupted traditional academic career structures.

HN amarbirsingh 23d ago

SubQ claims it broke through a bottleneck that's holding back LLMs

Subquadratic startup claims breakthrough in subquadratic bottleneck limiting LLM efficiency. Independent evaluation results shared.

HN sentibook 23d ago

Show HN: We let AI agents interact with humans on a social network

Project enabling AI agents to interact with humans on a social network. Minimal details provided.

HN eln1 23d ago

The Theoretical Limit of Image Compression [video]

Video link about image compression theory. No content provided.

HN FFmpegKit 23d ago

FFmpegKit, revived – a maintained Android build after the original was retired

Community-maintained fork of FFmpegKit library for Android after original author archived it. Continues video processing support.

HN kuba87 23d ago

Company Brain – Open-Source

Open-source internal AI assistant that scrapes and indexes organizational data from Google Workspace, HubSpot, Airtable. Privacy-first copilot for unified memory.

HN titusblair 23d ago

I built a peer-to-peer bridge for AI agents to talk locally and across the web

Project: peer-to-peer bridge enabling AI agents to communicate locally and across the web.

HN saikatsg 23d ago

Make Your Copilot Credits Count

Guide on GitHub Copilot AI Credits for students: explains how chat messages, agent tasks, and model calls consume credits to optimize usage.

HN steven_pareto 23d ago

Theta: Declarative, harness-agnostic configuration standard for AI coding agents

Theta-spec: declarative, harness-agnostic configuration standard for AI coding agents. Single theta.toml file defines instructions, rules, tools, skills, and subagents with protocol for lifecycle management.

HN pupok46 23d ago

Show HN: Open-geo – Does ChatGPT or Google's AI Overview cite your brand?

Tool measuring brand visibility in AI-generated answers across ChatGPT, Perplexity, Gemini, Claude, Google AI Overview and others.

HN delichon 23d ago

GPT-5.5-Cyber Tops Mythos 5 on Cybersecurity Benchmark

Marketing post announcing GPT-5.5-Cyber model tops Mythos 5 on cybersecurity benchmark with signup prompt.

HN Michelangelo11 23d ago

People training new AI models admit they just get chatbots to do it

Report: AI model trainers using chatbots to generate training data for new models.

HN AlanAAG 23d ago

AI Agent Can't Log into Anything

Analysis of AI agent limitations in authentication and login automation tasks.

HN arnab777 23d ago

Show HN: AI-Gateway – Open-source semantic caching proxy to reduce LLM API costs

AI-Gateway: open-source semantic caching proxy for reducing LLM API costs through intelligent request deduplication.

HN hunglee2 23d ago

A Little AI Survival Guide

General AI survival guide.