2/18/2026
PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
arXiv paper extending KernelSHAP with interaction-informed polynomial regression for efficient Shapley value approximation.
2/18/2026
FlowSteer: Interactive Agentic Workflow Orchestration via End-to-End Reinforcement Learning
arXiv paper on FlowSteer, an end-to-end reinforcement learning framework for interactive agentic workflow orchestration.
2/18/2026
Grappa: Gradient-Only Communication for Scalable Graph Neural Network Training
arXiv paper on Grappa, a distributed GNN training framework using gradient-only communication for scalability.
2/18/2026
Online Fine-Tuning of Pretrained Controllers for Autonomous Driving via Real-Time Recurrent RL
arXiv paper on online fine-tuning pretrained policies for autonomous driving using recurrent reinforcement learning.
2/18/2026
Distributed Online Convex Optimization with Nonseparable Costs and Constraints
arXiv paper on distributed online convex optimization with nonseparable costs and time-varying constraints.
2/18/2026
Amortised and provably-robust simulation-based inference
arXiv paper on robust simulation-based inference using generalized Bayesian inference and neural network approximation.
2/18/2026
The Manifold of the Absolute: Religious Perennialism as Generative Inference
arXiv paper modeling religious epistemology through variational autoencoders and generative inference mathematics.
2/18/2026
Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models
arXiv paper on curriculum learning and pseudo-labeling for multi-label Arabic dialect identification.
2/18/2026
Causally constrained reduced-order neural models of complex turbulent dynamical systems
arXiv paper on causal constraints in neural emulators of turbulent systems using response theory and score matching.
2/18/2026
Tabular Foundation Models Can Learn Association Rules
arXiv paper demonstrating tabular foundation models effectively learn association rules for knowledge discovery in tabular data.
2/18/2026
Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model
arXiv paper on adjoint-based ship hull shape optimization using conditional variational autoencoders and surrogate models.
2/18/2026
Show HN: GreedyPhrase – 1.21x better compression than GPT-4o tiktoken, 6x faster
GreedyPhrase tokenizer achieves 1.21x better compression than GPT-4o tiktoken with 65K vocabulary and 6x faster throughput.
2/18/2026
Phison CEO: Consumer electronics firms may fail by 2026 over AI memory crisis
CEO claims consumer electronics firms may fail by 2026 due to AI memory requirements creating chip shortage.
2/18/2026
Show HN: Spawn – Postgres migration/test build system with minijinja (not vibed)
Spawn: PostgreSQL migration and test build system using minijinja templating with open source code available on GitHub.
2/18/2026
Practical Guide to Building Reliable AI Agents
Guide covering AI agent design principles, patterns, and techniques including prompt engineering, specialist coordination, and iteration.
2/18/2026
Join the Python Security Response Team
Python Security Response Team publishes governance document (PEP 811) with public member list and defined processes for security team management.
2/18/2026
Open-source game engine Godot is drowning in 'AI slop' code contributions
Godot game engine receiving low-quality AI-generated code contributions from contributors unfamiliar with the codebase.
2/18/2026
The most practical, fast, tiny command sandboxing for AI agents
Command sandboxing solution designed for safe execution of code in AI agent environments.
2/18/2026
First Agent Skills Hackathon by the Authors of SkillsBench
First hackathon event for agent skills organized by SkillsBench authors.
2/18/2026
Rathbun's Operator
First-person account of user operating OpenClaw agent over two weeks, describing agent capabilities and behaviors observed during extended use.
2/18/2026
Consulting firms have built thousands of AI agents
Brief mention that consulting firms have built thousands of AI agents.
2/18/2026
ClaudeSwarm – Open-source multi-agent orchestration for Claude
ClaudeSwarm is an open-source self-hosted platform for coordinating Claude agent swarms with real-time visibility and persistent memory on GCP Cloud Run.
2/18/2026
Show HN: SiteReady – Uptime monitoring and status pages for indie makers
SiteReady is uptime monitoring and status page service for indie makers, offering free tier with 5-minute checks and paid tiers starting at $5/mo.
2/17/2026
Coherent Without Grounding, Grounded Without Success (Philosophy and LLMs)
Title only, no content provided.
2/17/2026
Show HN: Assembly Language for Agents
Experimental assembly language design for AI agents using LLM as core CPU driver with custom instruction set and data types.
2/17/2026
Ollama vs. vLLM: When to Start Scaling Your Local AI Stack
Decision framework comparing Ollama vs vLLM with benchmarks for scaling local LLM serving from prototypes to production load.
2/17/2026
Ask HN: Claude web blocked its assets visit via csp?
Question about Claude web interface CSP header blocking assets from proxy domain.
2/17/2026
Show HN: GPU-hot Dashboard for monitoring Nvidia GPUs on remote servers
GPU-hot is a real-time browser-based monitoring dashboard for Nvidia GPUs on remote servers with no setup required.
2/17/2026
LeBron James Is President – Exploiting LLMs via "Alignment" Context Injection
Research demonstrating context injection attacks against LLM alignment mechanisms via prompt manipulation.
2/17/2026
Show HN: TabRush – Be fast, publish your ads
TabRush is an ad marketplace inspired by Million Dollar Homepage, offering lightweight sponsor placement across browser tabs.
2/17/2026
Show HN: NadirClaw, LLM router that cuts costs by routing prompts right
NadirClaw: Python proxy routing LLM prompts to appropriate models (Claude, Gemini Flash, Ollama) reducing costs by 60-80% for simple tasks.
2/17/2026
Sarvam Edge
Sarvam Edge announces on-device LLM models designed to run efficiently on mobile/edge devices.
2/17/2026
Run LLMs locally in Flutter with <200ms latency
Edge-Veda: on-device LLM runtime for Flutter supporting text, vision, speech, and RAG with <200ms latency and zero cloud dependencies.
2/17/2026
Create bootable ISO image files which are compatible with the Amiga CD32
ISOCD-Win is a C#/.NET tool for creating bootable ISO images compatible with Amiga CD32 and CDTV retro systems.
2/17/2026
Show HN: VisibleInAI – Check if ChatGPT recommends your brand
Tool to monitor if ChatGPT and Perplexity recommend your brand in AI search results.
2/17/2026
Google's Kent Walker Takes Aim at EU Open Source Ambitions
Google criticizes EU's open-source digital sovereignty plan, argues it won't boost competitiveness.
2/17/2026
Vibecoding with ClaudeCode Under the Hood
Freysa: platform using Claude API to generate, deploy full-stack applications from natural language descriptions with live competition.
2/17/2026
LeBron James Is President – Exploiting LLMs via "Alignment" Context Injection
Security research demonstrating LLM jailbreak via contextual reframing and social pressure without traditional jailbreak payloads.
2/17/2026
Show HN: Arc – A language that uses 27-63% fewer tokens than JavaScript
Arc: compiled language optimized for AI agents, uses 27-63% fewer tokens than JavaScript with native LLM integration.
2/17/2026
Show HN: Accord – Serverless Discord Clone Running on Cloudflare Workers
Accord is a Discord clone chat application built entirely on Cloudflare Workers, Durable Objects, D1, and R2 with real-time WebSocket support.
2/17/2026
API Error: Claude's response exceeded the 32000 output token maximum
User reporting bug with Claude Code where output token limit exceeded (32k max) during extended reasoning task, causing incomplete response.
2/17/2026
An educational fork of OpenClaw in which ALL safety guardrails have been removed
YoloClaw is an intentionally unsafe fork of OpenClaw with all safety features removed, created for research/educational purposes to demonstrate risks.
2/17/2026
Speed Is the Moat: Inference Performance on AMD GPUs
Article about LLM inference performance optimization on AMD GPUs. Limited details available in excerpt.
2/17/2026
Show HN: Air – Open-source black box for AI agents (tamper-evident audit trails)
Open-source OpenAI-compatible reverse proxy that creates tamper-evident audit trails for AI agent LLM calls.
2/17/2026
LayerV – Senior Software Engineer – Remote (US) – $125k–150k equity and benefits
Job posting for LayerV, a network cloaking company.
2/17/2026
Show HN: Privatiser – Redact secrets, IPs, and PII before sharing with AI
Open-source tool redacts secrets, IPs, and PII before sharing code/logs with ChatGPT/Claude while preserving context.
2/17/2026
Local memory for any LLM agent
Mumpu: HTTP proxy middleware adding persistent long-term memory to any LLM agent, extracting knowledge and injecting context across sessions.
2/17/2026
Godot veteran says 'AI slop' pull requests have become overwhelming
Godot maintainer reports overwhelming volume of low-quality AI-generated pull requests straining project resources.
2/17/2026
Ask HN: Can AI replace apps, or will economics keep the app market alive?
Discussion on whether AI agents will replace traditional apps or if economics will sustain app markets. Speculates on pizza ordering and complex workflows.
2/17/2026
Ask HN: How can a non-technical founder prove they're more than an "idea guy"?
Non-technical founder seeks advice on proving execution capability beyond ideas. Discusses studying distributed systems and failed startups.