10h ago
Harness Handbook
Open-source handbook on agent harnesses from Tencent, covering auditability and editability of coding agents. Original documentation on AI agent infrastructure.
11h ago
Why AI Is Collapsing: How China Is Winning [video]
Video essay on AI market collapse and China's competitive position.
11h ago
Show HN: 9lives – Self-healing test runner that refuses to mask real bugs
9lives is a self-healing test runner that automatically fixes broken Playwright tests by classifying failures and healing them in tiers, designed to prevent AI agents from unnecessarily rewriting tests.
11h ago
Show HN: Willow Voice – Free AI Dictation
YC S24 company shipping Scribe (style-learning dictation) and free AI dictation using fine-tuned Llama 3.1 8b.
11h ago
The 2025–2026 Evolution of Generative Spatial AI
Technical retrospective on generative spatial AI advances: text-to-mesh, video, 3D models, world generators, CAD integration.
11h ago
I Think I Know How to Solve the Video Game Industry's Problems
Title only, appears to be spam or placeholder content about unrelated video game industry topic.
11h ago
The Joy of Old-School Coding After a Stupid Mistake
Blog post about debugging a coding error. Opinion piece with minimal technical substance.
11h ago
Migrating from GitLab to Forgejo
Personal account of migrating from GitLab to Forgejo due to resource constraints. No technical depth or original research.
11h ago
Chatbots Can Go into a Delusional Spiral. Here’s how it happens.
Title only. Discusses LLM failure modes involving delusional/circular reasoning in chatbots.
11h ago
Show HN: GenUI, native SwiftUI interfaces generated by AI agents
Show HN: GenUI enables AI agents to generate real, interactive SwiftUI interfaces for iOS/macOS instead of text output.
12h ago
Memory is needed for more than just weights
Research on memory requirements for LLMs beyond weight storage.
12h ago
Into big air: paragliding's extreme frontier
Title only. Sports content unrelated to tech interests.
12h ago
Show HN: NoMac – let your AI agent ship iOS apps without a Mac
Show HN: NoMac builds, tests, and ships iOS apps via cloud Macs without local hardware. Agent-first with TestFlight/App Store integration.
12h ago
The fix for my AI agent wasn't making it smarteR
Title only. Personal experience improving AI agent performance without scaling model size.
12h ago
Meta AI image detector fails to identify some of its own cropped AI images
Meta's AI image detector fails to identify cropped versions of its own generated images.
12h ago
Generalizing LLMs to PLTs: Probabilistic Language Tries
Research generalizing language models to probabilistic language tries as alternative architecture.
13h ago
I made an LLM think in latent space. The model never read a single thought
Research on LLM internal reasoning in latent space without generating intermediate text outputs.
13h ago
Show HN: Token Governor – The cheapest LLM token is the one you never send
Tool to optimize LLM token usage by reducing unnecessary token sends, focusing on cost reduction strategies.
14h ago
Truth is not a direction: a Tarski attack on LLM probes
Research paper analyzing LLM probes using Tarski's work, questioning whether truth is directional in model representations.
14h ago
Show HN: Postern, an email system for both humans and agents
Email system enabling AI agents to have addresses and respond to emails with unified inbox and optional Vectorize integration on Cloudflare Workers.
14h ago
Show HN: Tiny ONNX Runtime Web Worker Starter
Starter template for running ONNX Runtime in browser Web Workers to keep UI thread responsive during model inference on mobile and desktop.
15h ago
The AI Picbreeder Experiment
Explores whether AI agents can be creative and interact autonomously, treating agents as model organisms for cultural production rather than tools.
15h ago
Ask HN: Burned Tokens scented candle ideas
Humorous question about scented candle concept. Off-topic novelty post.
21h ago
Optimizing Database Performance: Tips and Tricks for Faster Web Applications
Generic web performance optimization article covering database tuning and user experience metrics.
22h ago
ADDing agent-context annotations for existing API specs
ADD standard enabling IoT devices to self-describe to AI systems via JSON documents for safe agent integration without custom code.
22h ago
Why LLMs get dates and times wrong (and how to fix it)
Technical analysis of LLM temporal reasoning failures and solutions using temporal infrastructure in scheduling agent systems.
22h ago
Show HN: AI Humanizer – Rewrite AI text into natural copy
Tool converting AI-generated text to natural copy for publishing across content platforms.
22h ago
Show HN: Makoto the Claude Code plugin that keeps the AI honest
Makoto plugin monitoring Claude Code agent tool calls for truthfulness, blocking fabricated actions via integrity verification.
22h ago
China may restrict foreign access to Chinese open-source AI models
China may restrict foreign access to Chinese open-source AI models.
22h ago
Can AI Answer the $3T Question?
Analysis of AI infrastructure investment returns and whether $3T spending on AI can be justified economically.
23h ago
Why Industry 5.0 is more than AI-powered analytics
Panel discussion on Industry 5.0 and AI-led decision-making in Indian manufacturing sector.
23h ago
Promising inference software, written in Zig
ZML/LLMD: Self-contained LLM inference server supporting LLaMa/Gemma/Qwen/Mistral across 5 architectures with continuous batching and tool calling.
23h ago
Turn off this Meta setting before someone generates AI images of you
Meta's new image generation model generates images from Instagram accounts without explicit user consent.
23h ago
TinyToT – Tree of Thoughts Inference Server
TinyToT: Ollama-compatible inference server using knowledge retrieval and reasoning chains, 97% benchmark score, runs on CPU in <1ms.
23h ago
AI subscriptions cut quotas and raised prices in early 2026
AI subscription services raised prices and cut quotas in early 2026, reducing value proposition.
1d ago
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
Game theory framework for principal-agent interactions with calibrated forecasts instead of direct action observation.
1d ago
Conformal Predictive Programming for Chance Constrained Optimization
Framework for solving chance-constrained optimization problems using conformal prediction and quantile methods.
1d ago
Data Alchemy: Mitigating Cross-Site Model Variability Through Test Time Data Calibration
Stain normalization method for histopathology imaging to reduce cross-site variability in deep learning deployment.
1d ago
Joint Bayesian Parameter and Model Order Estimation for Low-Rank Probability Mass Tensors
Method for joint Bayesian parameter and model order estimation using low-rank tensor decomposition.
1d ago
($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces
Framework for parametric multi-task optimization with non-fixed and infinite task spaces.
1d ago
ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access
Token-domain multiple access scheme using large models for semantic recovery in token communications.
1d ago
Bayesian Deep Learning for Discrete Choice
Research on Bayesian deep learning applied to discrete choice models for econometrics and decision-making analysis.
1d ago
Douglas-Rachford Splitting for Group-Sparse Feedback Linear-Quadratic Control
Douglas-Rachford splitting algorithm for distributed and sparse feedback linear quadratic control problems.
1d ago
Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
Robustness analysis of LLM ranking systems showing top model rankings are sensitive to removing small preference data subsets.
1d ago
A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
Vision toward energy-efficient domain-specific AI models and agents, addressing sustainability in LLM and AI deployment.
1d ago
Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery
Recovery from linear measurements under sparse adversarial corruption with robustness guarantees beyond exact recovery conditions.
1d ago
SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
SeFA-Policy improves visuomotor policy learning using selective flow alignment to reduce accumulated error in robotic imitation learning.
1d ago
MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs
Meta-path induced hypergraph contrastive learning method for node importance estimation in heterogeneous knowledge graphs.
1d ago
A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding
Tool bottleneck framework for medical image understanding using vision-language models and specialized tool composition.
1d ago
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
Representation-as-a-Judge approach using small language models for efficient evaluation without generation, exploiting semantic capacity asymmetry.