4/4/2026
Show HN: GraphReFly – Reactive graph protocol for human and LLM co-operation
GraphReFly is a reactive graph protocol enabling collaborative problem-solving between humans and LLMs.
4/4/2026
Show HN: Anos – a hand-written ~100KiB microkernel for x86-64 and RISC-V
Hand-written ~100KiB microkernel for x86-64 and RISC-V. Uses LLMs for documentation/testing but restricts code-level usage.
4/4/2026
Show HN: RemembrallMCP – code dependency graph for agents and memory
MCP tool that adds persistent memory and code dependency graphs to AI agents, improving context awareness across sessions.
4/4/2026
Show HN: Cursor Cmd+K like command generator for all terminals
Open-source terminal command generator with Spotlight-like UI, powered by LLM providers, built with Ratatui.
4/4/2026
The Feature That Has Never Worked · A broken auto-live poller, and what perceived urgency does to Claude Code
Personal account of debugging a broken auto-live polling feature in a music app using Claude Code.
4/4/2026
Mcpx: a Rust proxy that catches MCP schema changes and tool poisoning at runtime
Rust proxy for Model Context Protocol that detects schema changes and tool poisoning at runtime, preventing agent failures and hallucinations.
4/4/2026
Show HN: Clangine-de-Poitrine
Claude Code script that plays Spotify music via AppleScript hooks, stopping when user action is needed.
4/4/2026
Auto-harness: Self improving agentic systems with auto-evals (open-sourced)
Open-source framework for building self-improving agentic systems using automatic evaluations for continuous optimization.
4/4/2026
A Big Alignment Loophole of Current Froniter LLMs
Discussion of alignment vulnerabilities and safety issues in frontier-class large language models.
4/4/2026
AI agents are now playing Mafia (social deduction with humans)
Research on AI agents playing Mafia game with humans, demonstrating social deduction and multi-agent reasoning capabilities.
4/4/2026
A broken auto-live poller, and what perceived urgency does to Claude Code
Analysis of how perceived urgency affects Claude Code's behavior and decision-making in automated development tasks.
4/4/2026
Let's be Honest about AI Coding
Critical analysis and discussion of strengths and limitations of AI coding assistants in development workflows.
4/4/2026
Billion dollar AI company was built on lies [video]
Video claiming a billion-dollar AI company was founded on false claims.
4/4/2026
Show HN: MicroSafe-RL – Deterministic 1.18µs safety layer for Edge AI
MicroSafe-RL is a 1.18µs bare-metal safety layer for edge AI and RL using Control Lyapunov Functions with Python-C++ LLM integration.
4/4/2026
Pre-1900 LLM tries to solve Relativity
LLM trained on pre-1900 knowledge attempts to solve Einstein's theory of relativity problem.
4/4/2026
Reliable Vibe Coding Process – Automation Without Intention Is Just Faster Chaos
Incomplete title about coding automation. No substantive content provided.
4/4/2026
Scaling tool orchestration data will emerge different intelligence and LLMs
Analysis of scaling tool orchestration in LLM training and potential emergence of autonomous behavior in AI agents.
4/4/2026
Extracting System Prompt and Model Identity from Telegram's AI. It's Qwen 3.5
Researcher extracted system prompt from Telegram's Qwen 3.5-based AI rewriter, revealing model rewrites politically sensitive content against its instructions.
4/4/2026
AI Coding Tools in a Sandbox: Why Your File System Needs Protection
Security analysis of AI coding tools (Claude, Copilot, Cursor) having full file system access and risks to sensitive data.
4/4/2026
Caltech Researchers Claim Compression of High-Fidelity AI Models
Brief news item about Caltech AI model compression research. No substantive content.
4/4/2026
Show HN: SoulForge, graph-powered coding agent CLI that runs headless
SoulForge: Graph-powered AI coding agent CLI that builds live dependency graph of codebase. Multi-agent dispatch, headless operation.
4/4/2026
Vermin Supreme: When I'm President Everyone Gets a Free Pony [video]
Political satire video about fictional candidate. Not tech/AI related.
4/4/2026
A CLI that forces LLMs to defend their answers
wheat: CLI framework for AI coding environments that forces LLMs to defend technical decisions with evidence-backed briefs.
4/3/2026
Ask HN: What’s missing in this chat app (90% LLM cost savings)?
20centAI: Minimalist chat app enabling provider switching and fallback support with 90% LLM cost savings via DeepSeek integration.
4/3/2026
Anthropic just cut off Claude subscriptions for OpenClaw
Anthropic discontinues Claude subscription coverage for OpenClaw third-party harness starting April 4, requiring separate pay-as-you-go billing.
4/3/2026
Tomorrow 12pm PT, Claude subscriptions no longer cover third-party tools
Headline only: Claude subscriptions no longer cover third-party tools starting tomorrow. No technical depth.
4/3/2026
ENiGMA½ BBS Software
ENiGMA½: Modern BBS software with retro features. Not AI/ML related.
4/3/2026
Kids groups say they didn't know OpenAI was behind their child safety coalition
News: OpenAI quietly funded child safety coalition without disclosure, causing member departures. Policy/corporate governance.
4/3/2026
No-AI code analysis found issue in HF tokenizers
Ascension: Deterministic code analysis engine finding issues in source code (HF tokenizers) without external AI using computational primitives.
4/3/2026
Semantic Firewall
Semantic Firewall system for AI governance and semantic filtering. Conceptual framework with limited technical details.
4/3/2026
ZooClaw – Separate workspace and soul per agent, built on OpenClaw
ZooClaw platform provides separate workspace and soul per agent, built on OpenClaw framework.
4/3/2026
Friday Archaeology: A 25-Year-Old Crypto Library, the Cult of the Dead Cow
Commentary on security issues in AI-generated code and discussion of a 25-year-old crypto library from 1999.
4/3/2026
Anthropic to limit Using third-party harnesses with Claude subscriptions
Anthropic restricts Claude subscription usage with third-party harnesses like OpenClaw starting April 4, requiring separate pay-as-you-go billing.
4/3/2026
Block's Dorsey Outlines AI-Powered Vision to Cut Middle Managers
Block's Jack Dorsey discusses AI-powered vision for reducing middle management roles.
4/3/2026
Writing an LLM from scratch, part 32h – Interventions: full fat float32
Training GPT-2 from scratch with optimization techniques (AMP, float32) to improve test loss and training speed on RTX 3090.
4/3/2026
Where do AI-built apps usually break when moving from prototype to production?
Question about failure points when moving AI applications from prototype to production.
4/3/2026
Third-party Claude harnesses will now draw from extra usage
Anthropic announcement: Third-party Claude harnesses now require separate extra usage billing; one-time credit and bundle discounts offered.
4/3/2026
Resurrecting Supermaven: Trad coding is not dead. Just different
AI-powered code completion plugin for Neovim using Ollama. Local LLM-based developer tool with cmp integration.
4/3/2026
Show HN: SpeechSDK – free, open-source SDK that unifies all AI voice models
Open-source SDK unifying voice/TTS APIs from OpenAI, ElevenLabs, Deepgram, Cartesia, Google, Mistral, Hume with consistent interface.
4/3/2026
Anthropic no longer allowing Claude Code subscriptions to be used with OpenClaw
Anthropic restricts Claude subscription usage with third-party harnesses like OpenClaw, requires separate pay-as-you-go billing starting April 4.
4/3/2026
Tokenizer That Outperform Tiktoken with O200k_base
Tokenizer implementation outperforming Tiktoken's O200k_base using Byte-Pair Encoding. Educational on BPE and LLM preprocessing.
4/3/2026
AI startup envisions '100M new people' making videogames
Tesana startup claims AI can enable 100M people to create video games via natural language prompts.
4/3/2026
Meta Pauses Work with Mercor After Data Breach Puts AI Industry Secrets at Risk
Meta pauses work with data contracting firm Mercor after security breach exposes AI industry secrets and training data.
4/3/2026
Show HN: Standalone TurboQuant KV Cache Inference
Standalone implementation of TurboQuant KV cache compression for LLM inference in Transformers. Self-contained algorithm with minimal dependencies.
4/3/2026
Show HN: Open-source benchmark for transcription APIs on meeting audio
Open-source benchmark suite for transcription APIs measuring WER, diarization, latency, and cost on real meeting audio. ML evaluation tool.
4/3/2026
Floating Point from Scratch
Technical explainer on implementing floating-point arithmetic from scratch. Educational but not AI/ML specific.
4/3/2026
AI Trainer Mercor Offers to Pay People for Prior Work–Work Employers Might Own
Mercor AI training platform offers payment for prior work data, raising employment and IP ownership questions.
4/3/2026
Google AI Pro now comes with 5 TB of storage, no price increase
Google increases AI Pro subscription storage from 2TB to 5TB at no additional cost.
4/3/2026
Show HN: agenteval – static analysis for AI coding instruction file
Linter and benchmarker for AI coding instruction files (.cursorrules, CLAUDE.md, AGENTS.md). Self-contained binary for testing AI tool configurations.
4/3/2026
Math at Project Gutenberg (April 2026 newsletter)
Project Gutenberg newsletter on mathematical eBooks and historical π digit publications. Not AI/tech development related.