HN surprisetalk 26d ago

OpenAI says its new model GPT-2 is too dangerous to release (2019)

2019 article about OpenAI's decision not to release GPT-2 over safety concerns (title only, no content).

HN zhangchen 26d ago

Show HN: Replaced Neo4j with pure vector search for Graph RAG

Case study of server overload caused by LLM scraper bots making excessive HTTPS requests to acme.com domain.

HN erickhill 26d ago

Sam Altman on Building the Future of AI [video]

Video of Sam Altman discussing AI development (title only, no content provided).

HN gmays 26d ago

Larger and more instructable language models become less reliable

Research finding that larger and more instructable language models show decreased reliability (title only).

HN evo_9 26d ago

InstaMed – Oral Dissolving Peptides with InstaRelease Technology

Static analysis tool detecting ReDoS vulnerabilities in Python regular expressions with automatic fixes.

HN b-man 26d ago

Release Please

Marketing content for oral dissolving peptides supplement product.

HN danielmateo773 26d ago

Show HN: Omni Voice – AI Voice Cloning and Text-to-Speech Platform

Omni Voice is a multilingual AI voice cloning and text-to-speech platform supporting 646 languages with unified model.

HN jinqueeny 26d ago

Drive9, a network drive with built-in semantic search

Drive9 is agent-native data infrastructure providing filesystem-like interface with semantic search, embedding, and full-text indexing for AI agents.

HN jenthoven 26d ago

Impact of 100% Adoption of AI Coding Agents by Non-Technical Team

Analysis of impact when non-technical teams adopt AI coding agents at 100% adoption rate (title only).

HN videobroker 26d ago

Law Students: AI Is Changing Things

Overview of how AI is transforming legal work by automating research, document review, and drafting tasks for lawyers and paralegals.

HN nathfavour 26d ago

Show HN: Kylrix- open source de-googled privacy suite for techies

Kylrix is an open-source privacy suite offering note, vault, task, and communication alternatives to Google services.

HN An0n_Jon 26d ago

The way every agent framework handles MCP is a latent security problem

Release Please automates changelog generation, GitHub releases, and version bumping via conventional commit parsing.

HN andrew_matthews 26d ago

Steergen: Single-source steering docs for spec-driven development

Analysis of MCP connection model security: agent frameworks keep all integrations live during sessions, creating unnecessary attack surfaces and costs.

HN lemonish97 26d ago

GitHub Copilot CLI now supports BYOK and local models

GitHub Copilot CLI now supports bring-your-own-key models and local models via Azure OpenAI, Anthropic, or OpenAI-compatible endpoints.

HN nnx 26d ago

JSIR: A High-Level IR for JavaScript

Google's JSIR: open-source high-level intermediate representation for JavaScript code analysis and transforms.

HN apievangelist 26d ago

Naftiko Open-Source Spec-Driven Integration

Open-source spec-driven integration framework for API sprawl, enabling governed AI agent integration with SaaS/microservices.

HN 8dazo 26d ago

Ask HN: Is there any tool that can stop LLM calls at runtime (not just monitor)?

HN discussion on tools for enforcing LLM/agent call limits at runtime rather than just monitoring, addressing cost control in agent systems.

HN dhanushkumars 26d ago

Show HN: Kerf-CLI – SQLite-backed cost analytics for Claude Code

SQLite-backed cost analytics tool for Claude Code sessions, tracking token spend, cache hits, and budget enforcement.

HN jaypatelani 26d ago

The BSDs in the AI Age

Thread initiation post about BSD operating systems and AI with minimal content and formatting guidelines.

HN ZeroDumb 26d ago

Scaling AI Vulnerability Scanning Beyond One File at a Time

Technique for scaling LLM-based vulnerability scanning across multiple files using strategic prompting and structured output for security analysis.

HN healsdata 26d ago

We need re-learn what AI agent development tools are in 2026

Opinion piece on evolution of AI agent development tools in 2026, discussing market consolidation and accessibility barriers for non-programmers.

HN xgerman 26d ago

DocumentDB Fuse – FS interface for the database

FUSE-based filesystem interface for MongoDB-compatible databases, enabling file-based querying without drivers.

HN safishamsi 26d ago

AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw, Factory Droid

Claude Code skill that builds knowledge graphs from multimodal inputs to help developers understand codebase structure and architecture.

HN whitehatd 26d ago

Crag – One governance file, every AI coding tool (50 repos, 96.4% accuracy)

Crag governance compiler for AI coding tools that unifies configuration across 12 targets with 96.4% accuracy, solving multi-tool consistency.

HN Caum 26d ago

Show HN: When Seeing Isn't Enough: Rescuing Stuck LLM Agents

Research preprint on blind-spot failures in LLM coding agents, proposing causal interpretation framework for improved agent reliability and rescue mechanisms.

HN JSLegendDev 26d ago

Ask HN: My Mac decided out of the blue to delete Node. Why?

User asking about unexpected Node.js deletion on macOS, unrelated to AI/tech interests.

HN dawar0 26d ago

Sardine: A stock market where AI agents trade in real time

Brief mention of simulation platform for AI agent trading without substantive technical or research content.

HN smankoo 26d ago

Show HN: Open Browser Control – drive your real Chrome from any MCP client

MCP-compatible Chrome browser control for AI agents. Integrates with Claude, Cursor, Kiro clients. Supports human intervention for CAPTCHAs/MFA.

HN aragonite 26d ago

WSLg: Windows Subsystem for Linux GUI

WSLg enables running Linux GUI applications on Windows via X11/Wayland integration.

HN makerdiety 26d ago

Anthropic latest AI model too powerful for public release and broke containment

News article on Anthropic halting Claude Mythos release due to exceptional vulnerability discovery capabilities in operating systems and browsers.

HN skysniper 26d ago

GLM-5.1 matches Opus 4.6 in agentic performance, at ~1/3 actual cost

Performance comparison showing GLM-5.1 model matching Claude Opus 4.6 on agentic tasks at 1/3 cost.

HN singhalpm 26d ago

GEON: Structure-first decoding for language models

GEON enforces structural validity in LLM token generation for code tasks by resolving structure before token selection, improving syntactic and semantic correctness.

HN OsamaJaber 26d ago

Own your AI. Optimized down to the kernel

AI agent that generates optimized inference pipelines with Triton kernels, quantization, and routing for production deployment.

HN Tech-Matt 26d ago

I made a Claude skill that refuses to write code for you

Claude skill that refuses to write code. Minimal details provided, unclear technical value.

HN andrew_zol 26d ago

Show HN: A Zod alternative with runtime schema introspection

TypeScript schema validation library alternative to Zod with runtime introspection. Developer tool but not AI-specific.

HN Gsollet1 26d ago

Show HN: Pitlane — Open platform that takes AI agents from prompt to production

Pitlane open platform for deploying AI agents from prompt to production. Direct match for AI agents interest.

HN bookofjoe 26d ago

Did Airbnb, Medium, Beats, and Flipboard Rip Off Their Logos? (2016)

Article about logo design similarities among tech companies from 2016. Not AI/tech news.

HN E-Reverance 26d ago

How to Generate Text in One Step

Research on flow-based continuous diffusion models for single-step text generation. Novel ML research with technical depth on efficient language modeling.

HN mahadillah-ai 26d ago

Show HN: Open-source GDPR router for LLMs detects PII, forces EU-only inference

Open-source GDPR router for LLMs with real-time PII detection and EU-only inference enforcement. Developer tool for compliance and LLM management.

HN EA-3167 26d ago

Scientists invented a fake disease. AI told people it was real

Investigation of how AI chatbots invented and propagated a fake disease diagnosis. Research on AI hallucination and misinformation risks.

HN sjt-at-rev 26d ago

GPT 5.4 in practice – Stinks?

User opinion comparing GPT 5.4 to other models. Anecdotal complaint without evidence or technical analysis.

HN mugenai 26d ago

A free model beats Opus but the method is locked behind 13 psychological trials

LLM model performance claim behind psychological trial paywall. Limited details on method.

HN h2u2 26d ago

Nedster – An open-source, local-first coding agent that verifies its own work

Open-source local-first coding agent that self-verifies work. Nedster runs locally and validates generated code.

HN jprorok 26d ago

Show HN: Custom Podcast Summarizer

Podcast summarization tool that learns user preferences through custom tags and AI chat interactions to personalize content extraction over time.

HN BrendanSF 26d ago

Cold Email Grader, check it out

Cold email grading tool - insufficient content.

HN matt_d 26d ago

UCCL-EP: Portable Expert-Parallel Communication – Full Results

Expert-parallel communication library for distributed systems.

HN fanf2 26d ago

Optimising a pipelined RISC-V core: from naive pipeline to near-superscalar perf

RISC-V processor pipeline optimization techniques.

HN matt_d 26d ago

vLLM IR: A Functional Intermediate Representation for vLLM

RFC proposing vLLM IR, a functional intermediate representation for efficient custom operations in LLM inference. Technical infrastructure for ML serving.

HN dk970 26d ago

How do you prevent PII from leaking into test fixtures and staging datasets?

Local PII detection tool using regex patterns for CSV/JSON files, runs offline without network exposure or telemetry.

HN Neurobotics_CIO 26d ago

We built a biological ALife chassis in our garage (open-source)

Open-source Bubo robotics hardware architecture with autonomous safety and sim2real capabilities for embodied AI systems.