2/27/2026
Show HN: Caddy plugin that charges AI crawlers real USDC to access your site
Caddy middleware implementing HTTP 402 protocol to charge AI crawlers USDC on Base blockchain for content access.
2/27/2026
STRinGS: Selective Text Refinement in Gaussian Splatting
Framework for improving text reconstruction in 3D Gaussian Splatting scenes. Addresses preservation of fine-grained textual elements in 3D representations.
2/27/2026
Show HN: AI sandbox that runs on your homelab
Pixels is a sandbox running on TrueNAS homelab using Incus containers for testing AI agent CLIs without paid services.
2/27/2026
Perplexity Computer – The Age of AI Agents Is Here
Opinion piece on AI agents and workforce reduction, citing Jack Dorsey and Dario Amodei on automation of software engineering.
2/27/2026
Architectural Decisions That Will Make or Break Your AI Product
Essay on five architectural decisions for AI products based on real-world experience, covering cost and reliability pitfalls.
2/27/2026
Show HN: Httap – intercept and inspect HTTP traffic from your shell or agent
Httap is an HTTP proxy tool for terminal and AI agents to intercept, inspect, and mock HTTP traffic with automatic browser profile management.
2/27/2026
Show HN: Shannon – Local desktop app to orchestrate Claude Code agent teams
Desktop application orchestrating Claude Code agent teams with specialized roles. Enables dependency graphs, parallel/sequential workflows, and multi-model coordination.
2/27/2026
Show HN: We built a public CTF to stress-test AI agent guardrails
APort is a public CTF stress-testing framework for AI agent guardrails and safety mechanisms in autonomous financial systems.
2/27/2026
The Twilight of the Smartphone
Speculation on smartphone era ending due to new AI device project from designer Jony Ive.
2/27/2026
PewDiePie trains his own AI coding model [video]
Incomplete title-only entry about PewDiePie training an AI coding model.
2/27/2026
Show HN: Tchop.io – AI-powered community framework
Tchop.io is described as a fully AI-powered community framework with user control and ownership.
2/27/2026
FAR: Make Every File Readable to AI Coding Agents with Persistent .meta Sidecars
FAR uses persistent .meta sidecar files to augment file readability for AI coding agents, addressing 30-40% context blindness.
2/27/2026
Ask HN: Does "task-derived JD and evidence-based candidate" make hiring better?
System to generate job descriptions from real engineering tasks and evaluate candidates against code evidence from GitHub/Jira, PRs and diffs.
2/27/2026
Show HN: Dypai – Build back ends via MCP
Backend development framework using Model Context Protocol (MCP) for building systems with AI assistance.
2/27/2026
Show HN: AgentWeb – Free business directory API for AI agents (11M+ businesses)
Free business directory API with 11M+ businesses, full-text search and geo-location for AI agents to query real-world business data reliably.
2/27/2026
Governing Autonomous AI Agents in Production
Framework for governing autonomous AI agents in production environments, addressing safety and control.
2/27/2026
The Enshittificator [video]
Video about enshittification.
2/27/2026
LLMs Generate Predictable Passwords
Research on LLM-generated passwords being predictable, exposing security vulnerabilities in password generation tasks.
2/27/2026
Ask HN: Have LLMs sapped your motivation for open source?
Discussion about how LLM prevalence affects open source contributor motivation and reputation, questioning whether AI-generated code diminishes accomplishment recognition.
2/27/2026
" AI infrastructure is controlled by companies making toilets, MSG, and glass"
Commentary on concentration of AI infrastructure ownership among large conglomerates.
2/27/2026
Claude Code Skills and 380 agent skills from official dev teams and community
Collection of 380+ agent skills from Anthropic, Google, Vercel, Stripe and other teams for use with Claude, Codex, Gemini CLI and similar platforms. Real-world skills, not auto-generated.
2/27/2026
AI agents are fast, loose, and out of control, MIT study finds (ZDNET)
MIT study reports agentic AI moving mainstream with capabilities outpacing governance; notes OpenAI hired OpenClaw framework creator.
2/27/2026
AI Agent Crypto Wallets Create New Legal Risks, Investors Warn
Analysis of legal and regulatory risks from AI agents equipped with crypto wallets for autonomous transactions and hiring.
2/27/2026
Get free Claude max 20x for open-source maintainers
Anthropic offers 6 months free Claude Max 20x to open-source maintainers and contributors through rolling application review.
2/27/2026
Show HN: RunVeto – A Simple Kill Switch for Autonomous AI Agents
Kill switch governance tool for autonomous AI agents using LangChain, preventing agent sprawl and cost overruns from runaway recursion.
2/27/2026
The LLM App Isn't a Model, It's a System: Designing for Quarterly Model Swaps
Discusses designing LLM applications as systems built around models, planning for quarterly model swaps rather than model-centric architecture.
2/27/2026
Does journaling help people understand themselves long-term?
Discussion about journaling's long-term effects on self-understanding, unrelated to AI/tech interests.
2/27/2026
HikmaAI – The AI Agent Supply Chain is Broken. Here is how we fix it
Claim that AI agent supply chain has problems with proposed solutions, no substantive details provided.
2/27/2026
AI voice agents for hotels: lessons from 15,910 real guest calls
Case study of AI voice agents deployed in hotels analyzing 15,910 real guest interactions and lessons learned from deployment.
2/27/2026
AI Assisted Coding
Personal experience using AI-assisted coding with GLM 4.7/5 models and Claude CLI for debugging and development tasks, particularly Vulkan code.
2/27/2026
Show HN: Docsome – Single Markdown file to featured static documentation
Open source static documentation generator from single Markdown file with AI agent support via llms.txt format. Includes CLI tool, dark mode, search indexing.
2/27/2026
OpenAI and Amazon announce strategic partnership
OpenAI and Amazon announce multi-year strategic partnership with $50B investment. Joint development of Stateful Runtime Environment for enterprise AI.
2/27/2026
Introducing the Stateful Runtime Environment for Agents in Amazon Bedrock
Amazon Bedrock launches Stateful Runtime Environment for AI agents, powered by OpenAI models. Enables multi-step reliable agent execution with tool integration and operational controls.
2/27/2026
Joint Statement from OpenAI and Microsoft
Joint statement from OpenAI and Microsoft reaffirming their partnership and collaboration since 2019.
2/27/2026
Scaling AI for everyone
Funding announcement for AI company with $110B investment from SoftBank, NVIDIA, and Amazon. Strategic partnership with Amazon and NVIDIA for compute infrastructure.
2/27/2026
Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
Analysis of backdoor vulnerabilities in multimodal diffusion language models with self-purification defense mechanism.
2/27/2026
FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation
Benchmark evaluating LLMs on financial knowledge through exam questions and practical business reasoning scenarios.
2/27/2026
Deep Accurate Solver for the Geodesic Problem
Deep learning approach for computing accurate geodesic distances on continuous surfaces via polygonal mesh discretization.
2/27/2026
RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval
Training-free framework for multimodal information retrieval using MLLMs without large datasets or pre-training fine-tuning.
2/27/2026
Multi-Level Causal Embeddings
Framework for multi-level causal embeddings that generalize abstraction and preserve causal relations across coarse and detailed models.
2/27/2026
What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
Large-scale hypothesis screening of biological foundation models to understand what geometric and topological structures they learn from gene expression data.
2/27/2026
Decoding the Hook: A Multimodal LLM Framework for Analyzing the Hooking Period of Video Ads
Multimodal LLM framework analyzing video ad effectiveness by examining the first three seconds using visual, audio, and text analysis.
2/27/2026
Testable Learning of General Halfspaces under Massart Noise
Algorithm for testable learning of Massart halfspaces under Gaussian distribution with tester-learner framework.
2/27/2026
Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
Analysis of function vectors in LLMs showing they lack invariance across input formats despite targeting same concepts.
2/27/2026
SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
Testing framework to diagnose whether MLLMs genuinely read text in images or rely on parametric shortcuts in prompts.
2/27/2026
TopoEdit: Fast Post-Optimization Editing of Topology Optimized Structures
Topology optimization post-editing tool using structured latent embeddings for fast localized design revisions.
2/27/2026
mmWave Radar Aware Dual-Conditioned GAN for Speech Reconstruction of Signals With Low SNR
GAN-based speech reconstruction from mmWave radar signals captured through glass with low SNR using dual-conditioned architecture.
2/27/2026
LoBoost: Fast Model-Native Local Conformal Prediction for Gradient-Boosted Trees
Conformal prediction method for gradient-boosted trees that improves uncertainty quantification under heteroscedasticity without auxiliary models.
2/27/2026
GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
GetBatch: Object store API elevating batch retrieval to first-class operation for efficient ML data loading across storage clusters.
2/27/2026
veScale-FSDP: Flexible and High-Performance FSDP at Scale
veScale-FSDP: Enhanced FSDP distributed training framework supporting block-wise quantization and non-element-wise optimizers.