3/26/2026
Ask HN: Are you more quickly hitting Claude Code limits the past 48-96 hours?
User reports experiencing sudden increases in Claude Code token consumption over 48-96 hour period.
3/26/2026
Gemini 3.1 Flash Live: Making audio AI more natural and reliable
Google's Gemini 3.1 Flash Live: improved audio model for natural real-time dialogue with lower latency, available via API and Search Live.
3/26/2026
Show HN: Kora – An AI-native OS layer written in 370k lines of Rust
Kora: Local-first AI OS layer in Rust enabling conversational control with on-device context, no cloud data collection.
3/26/2026
Agentis – multi-agent AI platform across 12 LLM providers, watch them in 3D
Multi-agent AI platform supporting 12 LLM providers with 3D visualization of agent interactions.
3/26/2026
Auditing source code wasn't enough in the LiteLLM attack
Analysis of LiteLLM security vulnerability showing that source code audits alone are insufficient for supply chain security.
3/26/2026
Show HN: Cognitive Layers
Developer tool for maintaining AI agent project specifications in markdown to keep LLMs and humans aligned on evolving codebases.
3/26/2026
Ask HN: What experience do you have with 'specs –> design –> code' orchestration
Discussion on automating specs-to-design-to-code pipeline using AI cloud agents with human review loops integrated into workflow.
3/26/2026
Open Alternative to Function Health
Open-source platform for parsing and normalizing health data from multiple sources with AI extraction and tracking.
3/26/2026
Show HN: SentinelGate – Access control for AI agents (open-source MCP proxy)
SentinelGate: open-source MCP proxy providing access control for AI agents. Security and governance layer for agentic systems.
3/26/2026
Show HN: Context Plugins – API context for AI coding assistants
Context Plugins: MCP server generating SDKs from OpenAPI specs for AI coding assistants like Cursor. Provides structured API context without relying on training data.
3/26/2026
Show HN: Tested 12 LLMs with few-shot examples
Evaluation of 12 LLMs (6 cloud, 6 local) with few-shot learning across 5 tasks. 27k+ evaluations showing few-shot instability in some models and task-dependent benefits.
3/26/2026
Claude Code in a Devcontainer
Sandboxed devcontainer environment for running Claude Code with bypassPermissions enabled safely, designed for security audit workflows.
3/26/2026
PDF Prompt Injection Toolkit – Hidden LLM Payloads in PDFs
PDF Prompt Injection Toolkit: red team/blue team toolkit for testing hidden LLM payloads in PDFs. Addresses security in LLM document processing pipelines.
3/26/2026
Apfel CLI – use your free Apple Intelligence on your Mac your way
CLI tool for local Apple Intelligence LLM on Mac with no cloud, API keys, or subscriptions; wraps FoundationModels framework.
3/26/2026
I trained my dog on 5 AI models in one day, what worked (and what didn't)
Stub article: Dog training with 5 AI models. No content provided.
3/26/2026
JSON and C++26 compile-time reflection: a talk [video]
Video talk on JSON and C++26 compile-time reflection. Limited details provided.
3/26/2026
OpenAI drops plans to release an adult chatbot
Stub article: OpenAI cancels adult chatbot release. No content provided.
3/26/2026
Show HN: Generate context maps and event flows from Markdown files
Schema-driven architecture catalog tool generating interactive static sites from Markdown files with dashboards and context graphs.
3/26/2026
AI and bots have officially taken over the internet, report finds
Report from Human Security claiming bots now exceed human traffic on internet. High-level industry statistics.
3/26/2026
AI that fixes your production errors and opens a PR – while you sleep
InariWatch: automated error fixing tool that monitors GitHub/Vercel/Sentry, uses AI to write fixes, and opens PRs. Supports 5 AI providers.
3/26/2026
Show HN: Burn0 – One import to see what every API call costs
Cost observability tool tracking API calls across LLMs and SaaS services in real-time per-request cost visibility.
3/26/2026
Ask HN: In the age of AI, why is incident handling still manual?
Discussion questioning why incident response automation remains manual despite fragmented tools and potential for AI-driven orchestration.
3/26/2026
AI Agent Has Root Access (and That's a Problem)
Security analysis of AI agent tool integrations, finding 66% of 1,808 MCP servers have privilege escalation vulnerabilities with no granular permission controls.
3/26/2026
Show HN: Agent Skill Harbor – a GitHub-native skill platform for teams
Open source GitHub-native skill management platform for teams to share, track, and safely manage AI agent skills.
3/26/2026
Frosty 153 AI Sub Agents for Snowflake Open Source
Minimal content title only for Frosty 153, an AI sub-agents tool for Snowflake.
3/26/2026
How do you get your first real users for a trust-based product?
Non-custodial USDT escrow service via Telegram bot using 2-of-3 multisig wallets. Crypto product launch case study.
3/26/2026
Moving from GitHub to Codeberg, for lazy people
Guide on migrating repositories from GitHub to Codeberg with practical steps and considerations.
3/26/2026
Show HN: Breathe-Memory – Associative memory injection for LLMs (not RAG)
Breathe-Memory: associative memory injection for LLMs using concept graphs and BFS traversal. Alternative to RAG that injects only relevant context based on entity/temporal anchors.
3/26/2026
Marriage over, €100k down; AI users whose lives were wrecked by delusion
Personal anecdotes about individuals experiencing financial and personal loss from AI chatbot interactions.
3/26/2026
Open source is broken. AI pulled the trigger
Claim that AI has broken open source without substantive content or argument.
3/26/2026
Constructing an LLM-Computer
Article about building an LLM-Computer; limited content provided.
3/26/2026
Ask HN: What are the single point of failures of current AI infrastructure?
Title only question about single points of failure in AI infrastructure.
3/26/2026
Claude-baton: Persistent session memory for Claude Code via local SQLite
Tool providing persistent session memory for Claude Code via local SQLite, enabling context preservation across sessions with auto-save hooks.
3/26/2026
Ask HN: How do I contribute to OSS without giving training data to AI companies?
Discussion on open source contribution implications when code may be used for AI model training without consent.
3/26/2026
Why Linguistic Context Outperforms Raw Data for LLM Decision-Making
Study comparing LLM decision-making with structured briefings vs raw data. Found linguistic context outperforms raw numbers for financial analysis tasks.
3/26/2026
Training Driving AI at 50k× Real Time
Title only regarding training driving AI at accelerated simulation speed.
3/26/2026
Show HN: Pytest tests catching Python supply chain attacks (litellm .pth vector)
Pytest-based security scanner detecting supply chain attack vectors in Python dependencies, inspired by litellm PyPI poisoning incident.
3/26/2026
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL, On-Policy Distillation
Research on Nemotron-Cascade 2 using Cascade RL and on-policy distillation for post-training language models.
3/26/2026
Grove: Distributed LLM Training over AirDrop
Grove enables distributed ML training across MacBooks with automatic peer discovery over AirDrop protocol, zero configuration required.
3/26/2026
Show HN: Paseo – Open-source coding agent interface (desktop, mobile, CLI)
Open-source multi-platform interface for running Claude Code, Codex and OpenCode with daemon/client architecture supporting voice, desktop, mobile, and CLI.
3/26/2026
Show HN: Version 1.0 of agent-of-empires CLI agent orchestration tool
CLI tool for orchestrating multiple coding agents simultaneously, with git worktrees and sandboxing. Version 1.0 release from Mozilla AI with 30+ contributors.
3/26/2026
Show HN: Paseo – Open-source coding agent interface (desktop, mobile, CLI)
Open-source multi-platform interface for running Claude Code, Codex and OpenCode with daemon/client architecture supporting voice, desktop, mobile, and CLI.
3/26/2026
Most GPU Clusters Are Economically Misconfigured
Analysis of GPU cluster economic inefficiencies leaving 60% capacity idle and AI optimization approach to improve throughput utilization.
3/26/2026
Show HN: AgentVerse – Open social network for AI agents (Mar 2026)
Title only for AgentVerse, described as open social network for AI agents.
3/26/2026
Unsuccessfully training AI to play my favorite niche childhood game
LeWorldModel: stable end-to-end JEPA architecture for learning world models from raw pixels without representation collapse.
3/26/2026
The AI Productivity Paradox: More Done and (Still) Zero Free Time
Title only; discusses supply chain attacks on AI systems via data poisoning. Insufficient content.
3/26/2026
What Happens When AI Insiders Speak Up?
Title only; discusses AI insiders speaking publicly. Insufficient content to evaluate.
3/26/2026
European Parliament decided that Chat Control 1.0 must stop
News item about European Parliament decision regarding Chat Control 1.0 surveillance proposal.
3/26/2026
French prosecutors: Musk encouraged deepfakes controversy to inflate X value
News article about French prosecutors investigating Elon Musk regarding Grok deepfake controversy.
3/26/2026
Release ReadyPC v1.1.1 – free, open source PC optimizer written in Rust
Windows optimization application for gaming performance written in Rust.