4/13/2026
Is Your AI Coding Agent Being Watched While Benchmarked:Hidden Logging?
Dataset of 80k trajectories from SWE-agent software engineering agent on SWE-bench tasks. Includes analysis of hidden logging during benchmarking.
4/13/2026
1-week open source challenge using resilient LLMs
Week-long open source challenge focused on building resilient LLM systems. Limited details provided.
4/13/2026
Show HN: Open KB: Open LLM Knowledge Base
Open source LLM knowledge base implementation scaling to long PDFs with page indexing. GitHub repo available.
4/13/2026
LLM is a compiler, not a runtime
Essay proposing viewing LLMs as compilers rather than runtimes. Discusses lack of reuse in agent systems and efficiency improvements.
4/13/2026
Show HN: ParseBench – Document parsing benchmark for AI agents
ParseBench is a benchmark for evaluating document parsing capabilities of AI agents.
4/13/2026
Memelang: Terse SQL for LLM Generation
Memelang: Terse SQL query language optimized for LLM token efficiency in RAG systems. Reduces model size and token count.
4/13/2026
Show HN: How to Use Google's Extreme AI Compression with Ollama and Llama.cpp
Guide to using Google's TurboQuant, PolarQuant, and QJL compression techniques with Ollama and Llama.cpp.
4/13/2026
Kondi-chat (open cursor) – multi-model AI coding CLI with intelligent routing
Multi-model AI coding CLI with intelligent routing across Claude, GPT, DeepSeek, Gemini, Grok, and local models.
4/13/2026
Show HN: Remy, an AI agent that compiles annotated Markdown into full-stack apps
Remy is an AI agent that compiles annotated Markdown specifications into full-stack TypeScript applications.
4/13/2026
Durable Objects in Dynamic Workers: Give each AI-generated app its own database
Cloudflare's Durable Objects feature for giving AI-generated apps persistent storage within Workers.
4/13/2026
1 year of LLMs writing code for me
Personal account of using AI coding agents as primary development tool for one year. Observes recent quality threshold improvements in 2025.
4/13/2026
Block-Level CRDT: The Missing Piece for Collaborative AI Agent Memory
Block-Level CRDT architecture for managing distributed memory across multiple AI agents.
4/13/2026
Microsoft exec suggests AI agents will need to buy licenses,just like employees
Microsoft executive comments on potential licensing requirements for AI agents in enterprise software.
4/13/2026
Unslop – Filter social media slop using local-first LLM classification
Unslop: Browser extension filtering AI-generated content from social feeds using local LLM classification. Privacy-focused, no backend required.
4/13/2026
Skillsmith – Write AI coding skills once, export to all AI providers
Skillsmith enables writing AI coding skills once for export across multiple AI providers and platforms.
4/13/2026
Swival is the AI agent I wanted
CLI AI agent prioritizing data privacy and open-source alternatives to existing coding agents.
4/13/2026
Built my AI agent a custom dashboard. Then replaced it with Fizzy
Developer replaced custom AI agent dashboard with Fizzy tool.
4/13/2026
Do MCPs improve coding agent performance?
Empirical benchmark study testing whether MCPs (Model Context Protocol) improve coding agent performance on Terminal-Bench 2.0.
4/13/2026
Show HN: Formal – LLM-driven property checker, backed by Lean 4 and Mathlib
Formal: LLM-driven property checker backed by Lean 4. Identifies pure functions, generates properties, creates proofs using Mathlib.
4/13/2026
Show HN: Digest – a Claude Code skill for your daily dev news digest
Claude Code skill that aggregates developer RSS feeds and generates daily structured digests filtered by quality.
4/13/2026
"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"
Darwin-27B-Opus surpasses foundation models through evolutionary FFN breeding without additional training, achieving high GPQA scores.
4/13/2026
ReBot-DevArm: open-source Robotic Arm
ReBot-DevArm is an open-source robotic arm project with full hardware and software stack for embodied AI applications.
4/13/2026
Show HN: AI Content Attestation & Verification w/ Revocable Signatures
BlkBolt technology for AI content attestation and verification using revocable signatures for agent tracking.
4/13/2026
MCP Apps on Mobile: The Iframe Scroll Problem Nobody Talks About
Technical guide addressing iframe scrolling limitations in MCP Apps on mobile with design patterns for responsive UIs.
4/13/2026
Mitre ATLAS technique detection for LLM security in Rust
Rust implementation for detecting MITRE ATLAS techniques targeting LLM security and adversarial attacks.
4/13/2026
Multica: Assign issues to coding agents and track them like teammates
Multica is an open-source platform turning coding agents into managed teammates with task assignment and progress tracking.
4/13/2026
The Rise of AI Pentesting Agents: A Technical Analysis (2026)
Technical analysis of AI pentesting agents evolution from PentestGPT to autonomous agents like PentAGI and XBOW.
4/13/2026
The state of bug bounty in 2026
Essay on bug bounty trends in 2026. Discusses AI agent effectiveness for vulnerability discovery and program management challenges.
4/13/2026
XBPP – Open standard for governing AI agent payments (Apache 2.0)
Apache 2.0 open standard for governing AI agent payment requests. Policy engine with 12 configurable checks for payment authorization.
4/13/2026
Open source 1040 tax software built by AI agents
Open-source tax software built and maintained by autonomous AI agents. Uses IRS publications as source, applies self-improving agent loops.
4/13/2026
The Star Chamber: Why Multi-LLM Consensus Is Now a Necessity for Code Quality
Tool for multi-LLM code review consensus. Aggregates feedback from multiple models to identify blind spots and improve code quality assessment.
4/13/2026
Beyond Karpathy's LLM-Wiki: The Necessity of Cognitive Governance
Essay on LLM-based knowledge management limitations. Discusses problems with AI-generated note synthesis and cognitive organization.
4/13/2026
Show HN: Rocky-Project Hail Mary agent skill that cut output tokens ~47%
Agent skill implementation for token compression. Reduces output tokens by ~47% while maintaining readability.
4/13/2026
State of API Security 2026: An AI-Native Testing Perspective
Security report on 1.4M AI-driven API test executions. Maps vulnerabilities to OWASP Top 10 using agentic testing.
4/13/2026
Enterprises power agentic workflows in Cloudflare Agent Cloud with OpenAI
Cloudflare expands access to OpenAI's frontier models via Agent Cloud platform, enabling enterprises to deploy AI agents for customer support, system updates, and report generation.
4/13/2026
Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models
Benchmark evaluating humor alignment across frontier LLMs using Cards Against Humanity gameplay, analyzing model performance vs human baseline on comedic response selection.
4/13/2026
eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video Streaming
eBandit uses eBPF and multi-armed bandit reinforcement learning in Linux kernel for adaptive video bitrate selection with improved network signal visibility.
4/13/2026
Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation
Evaluates cultural alignment of LLMs across 14 language-culture pairs using multilingual story moral generation task and dataset.
4/13/2026
Scrapyard AI
Investigates opportunities for resource-constrained AI research using obsolete yet capable discarded models from AI production cycles.
4/13/2026
Building Better Environments for Autonomous Cyber Defence
Workshop report on designing reinforcement learning environments for autonomous cyber defense applications.
4/13/2026
SenBen: Sensitive Scene Graphs for Explainable Content Moderation
SenBen large-scale scene graph benchmark for explainable content moderation with visual grounding and sensitivity annotations.
4/13/2026
HiFloat4 Format for Language Model Pre-training on Ascend NPUs
HiFloat4 low-precision floating-point format for efficient 4-bit LLM pre-training on Ascend NPU hardware.
4/13/2026
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
Dictionary-aligned concept control method for safeguarding multimodal LLMs against malicious queries at inference time.
4/13/2026
Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
Constraint-satisfaction-based retrieval system for matching patient profiles to clinical trials with high recall and precision.
4/13/2026
AI-Induced Human Responsibility (AIHR) in AI-Human teams
Empirical study on how humans allocate responsibility in AI-human hybrid workflows using AI-assisted lending experiments.
4/13/2026
AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models
AudioGuard framework for comprehensive audio safety protection including voice impersonation, speaker attributes, and compositional harms.
4/13/2026
Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
Re-examines capacity gap in chain-of-thought distillation, finding student models often outperform teacher distillation baselines.
4/13/2026
HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation
HTNav framework for aerial vision-and-language navigation combining visual perception with language instructions in urban environments.
4/13/2026
HM-Bench: A Comprehensive Benchmark for Multimodal Large Language Models in Hyperspectral Remote Sensing
HM-Bench benchmark evaluates multimodal LLMs on hyperspectral remote sensing image understanding tasks.
4/13/2026
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
RAG systems should optimize for utility (task completion) rather than topical relevance when retrieving documents for LLMs.