Isolater - Feed

HN SaverioMazzi 6d ago

Simulating societies with LLM agents in TypeScript

WorldSim is a TypeScript multi-agent simulation engine for modeling how communities respond to policy changes using LLM-powered agent reasoning.

HN dkohlsdorf 6d ago

Show HN: LLMs as Planners, Not Reasoners

Hybrid question-answering system combining LLMs with Wikidata and Prolog for structured reasoning over knowledge graphs instead of pure RAG.

HN Growtika 6d ago

An Inside Look at OpenAI and Anthropic's Finances Ahead of Their IPOs

Financial overview of OpenAI and Anthropic ahead of potential IPOs.

HN JasonHEIN 6d ago

Openbrowser: A browser for agent without Chromium

Openbrowser is a headless browser built for AI agents using structured semantic state with element IDs instead of screenshots.

HN xer 6d ago

Show HN: Semantik, a vector broker that routes by semantic meaning

Semantik: vector message broker routing by semantic meaning using embeddings and SemQL query language for high-dimensional space.

HN HeinrichAQS 6d ago

Observability >> Predictability

Discussion of observability vs predictability testing approach for complex distributed systems.

HN danielmateo773 6d ago

Show HN: Seedance 2.0 – AI Video Generator for Text-to-Video and Image-to-Video

Seedance 2.0: multimodal text-to-video and image-to-video AI generator with unified architecture.

HN mantyx 6d ago

Show HN: M2a – Chat with remote agents from your terminal

m2a is a CLI tool for connecting to Agent2Agent protocol agents via HTTP+JSON/JSON-RPC with Bubble Tea chat UI and debug traces.

HN WraithVector 6d ago

Wraithvector-OpenClaw Integration

WraithVector governance layer intercepts OpenClaw agent tool calls to enforce policies, block dangerous actions, and generate audit evidence.

HN anup_sia 6d ago

Show HN: Per-user isolated environments for AI agents

Per-user isolated environments infrastructure for AI agents. HN post with limited content.

HN armen99 6d ago

KarpathyTalk – A positive developer community for builders and agents

KarpathyTalk is an open developer community platform with markdown posts, social features, and LLM-accessible APIs for builders and agents.

HN joozio 6d ago

AI is changing how small online sellers decide what to make

Small online sellers using AI tools like Alibaba Accio to automate product research and supplier discovery.

HN cmsefton 6d ago

China is winning one AI race, the US another – but either might pull ahead

Geopolitical analysis of US-China AI dominance race across research labs, academia, and startups.

HN tamnd 6d ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

TriAttention uses trigonometric KV cache compression to reduce memory by 10.7x while maintaining accuracy for long-context LLM agent reasoning.

HN dimitrismrtzs 6d ago

Ask HN: Is building a company around an open-source AI agent platform realistic?

Discussion of building commercial company on open-source AI agent platform wrapping Claude Code with custom MCP servers for infrastructure/operations.

HN radimm 6d ago

Don't let AI touch your production database

Production database safety concerns with AI-generated SQL. Models produce plausible but unreliable code lacking performance/locking awareness.

HN 8dazo 6d ago

Ask HN: How are you controlling costs and enforcing limits for LLM calls?

Discussion on production strategies for controlling costs and enforcing limits for LLM/agent systems to prevent unexpected loops and runaway expenses.

HN Farid046 6d ago

I built an autonomous AI team with a COO, QA engineer, and security auditor

PocketTeam: autonomous AI team with COO, QA engineer, security auditor roles using Claude Code. Self-healing, real-time monitoring, daily reports.

HN makerdiety 6d ago

As Meta Flounders, It Reportedly Plans to Open Source Its New AI Models

Meta plans to open-source its new AI models despite previous setbacks in AI leadership, investing over $600B in AI infrastructure.

HN hpcaitech 6d ago

The case for Model-as-a-Service over self-managed inference

Model-as-a-Service platforms abstract operational overhead of self-hosted inference. Discussion of hpc-ai.com built on Colossal-AI vs control tradeoffs.

HN vinodpandey7 6d ago

We long misjudged animal consciousness. Could AI be next? [video]

Video discussion of animal consciousness parallels to AI consciousness. Title only.

LB kirancodes.me by kirancodes 6d ago

Multi-agentic Software Development is a Distributed Systems Problem (AGI can't save you)

Research on using choreographic languages as a formalism for describing multi-agent LLM workflow coordination, framing it as a distributed systems problem.

HN morinoppp 6d ago

QitOS – A research-first framework for building serious LLM agents

QitOS is a research-first framework for building reproducible LLM agents with clean module design, benchmarks, and built-in observability.

HN gopiandcode 6d ago

Multi-Agentic Software Development Is a Distributed Systems Problem

Research on choreographic languages for managing multi-agent LLM coordination as a distributed systems problem with new programming language design.

HN 1659447091 6d ago

Businesses scramble to get noticed by AI search

Business impact of AI search engines. HubSpot experienced 140M lost visits as search behavior shifts toward AI-powered tools.

HN msolujic 6d ago

Addyosmani/agent-skills: Prod-grade skills for AI coding agents

Production-grade skills framework for AI coding agents. Encodes workflows, quality gates, and engineering best practices as reusable skills activated via slash commands.

HN _____k 6d ago

AI Agent Traps

Title only with minimal metadata. No substantive content provided.

Ax Zhaoting Gong, Ran Ran, Fan Yao, Wujie Wen 6d ago

AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems

AEGIS: Scaling homomorphic encrypted transformer inference via hybrid parallelism on multi-GPU. Privacy-preserving ML optimization, niche application.

Ax Thomas Manuel Rost 6d ago

Inference-Path Optimization via Circuit Duplication in Frozen Visual Transformers for Marine Species Classification

Circuit duplication technique for frozen vision transformer inference on marine species classification. ML optimization off-topic domain.

Ax Matthew Levinson 6d ago

MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents

MetaSAEs: Introduces decomposability penalty for training sparse autoencoders with atomic latents. Improves alignment and safety-relevant applications.

Ax Lamyea Maha, Tajmilur Rahman, Chanchal Roy 6d ago

Agile Story-Point Estimation: Is RAG a Better Way to Go?

Compares RAG vs standard approaches for Agile story point estimation in sprint planning. arXiv study on LLM application.

Ax Noshin Ulfat, Ahsanul Ameen Sabit, Soneya Binta Hossain 6d ago

Measuring LLM Trust Allocation Across Conflicting Software Artifacts

TRACE: Study on how LLMs allocate trust between conflicting code, documentation, and tests. Evaluates trustworthiness in AI-assisted software engineering.

Ax Kenan Tang, Jiasheng Guo, Jeffrey Lin, Yao Qin 6d ago

ExpressEdit: Fast Editing of Stylized Facial Expressions with Diffusion Models in Photoshop

ExpressEdit: Photoshop plugin using diffusion models for facial expression editing. Computer vision application, off-topic for interests.

Ax Ganlin Feng, Yuxi Long, Hafsa Ali, Erin Lou, Fahad Butt, Qian Liu, Yang Wang, Pingzhao Hu 6d ago

RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation

RDFace benchmark dataset for rare disease facial phenotype analysis in children with synthetic data generation. ML research but off-topic domain.

Ax Jacob Dineen, Aswin RRV, Zhikun Xu, Ben Zhou 6d ago

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

Introduces vocabulary dropout technique to solve diversity collapse in co-evolutionary LLM self-play curriculum learning. arXiv paper with novel method.

Ax Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii, Oleg Somov, Alexander Panchenko, Elena Tutubalina 6d ago

Evolutionary Search for Automated Design of Uncertainty Quantification Methods

LLM-powered evolutionary search automatically discovers unsupervised uncertainty quantification methods as Python programs for claim verification.

Ax Haocheng Tang, Xingyu Dang, Junmei Wang 6d ago

Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition

Fine-tuning approach adapting DeepSeek-OCR-2 for optical chemical structure recognition by formulating task as image-to-text.

Ax Mete Ismayilzada, Simone A. Luchini, Abdulkadir Gokce, Badr AlKhamissi, Antoine Bosselut, Antonio Laverghetta Jr., Lonneke van der Plas, Roger E. Beaty 6d ago

Large Language Models Align with the Human Brain during Creative Thinking

Study of brain-LLM alignment during creative divergent thinking tasks, measuring correlation between model performance and human neural activity.

Ax Xiaoan Liu, DaeHo Lee, Eric J Gonzalez, Mar Gonzalez-Franco, Ryo Suzuki 6d ago

VisionClaw: Always-On AI Agents through Smart Glasses

VisionClaw wearable AI agent on Meta Ray-Ban glasses combining egocentric perception with speech-driven task execution via OpenClaw agents.

Ax Zilin Huang, Zhengyang Wan, Zihao Sheng, Boyue Wang, Junwei You, Yue Leng, Sikai Chen 6d ago

Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving

Sim2Real-AD framework for zero-shot sim-to-real transfer of VLM-guided RL policies from CARLA simulation to physical autonomous vehicles.

Ax Michael Caosun, Sinan Aral 6d ago