Where the AI market is talking

Ask HN: Who wants to be hired? (May 2026)

Location: St. Augustine, FL Remote: Yes Technologies: • AI / GenAI: LLMs (OpenAI, Claude, Vertex AI, Llama), RAG, Agentic systems (LangChain, LangGraph, LlamaIndex), MCP, prompt engineering, chat + voice agents • Backend: Python (FastAPI, Django), Node.js, microservices, event-driven systems (Kafka, SQS), REST, GraphQL • Cloud: AWS, GCP, Docker, Kubernetes, CI/CD, observability • Frontend: React, Next.js, TypeScript • Data: PostgreSQL, MongoDB, Redis, embeddings, vector search • Tools & Standards: Git, Jira, Cursor, Claude Code, HIPAA, SOC 2 Type II, FHIR Resume/CV: https://drive.google.com/file/d/1P9hfg35-R_Z17Hx8SxJM4wqRtzU... Email: bryanmdavis25@gmail.com I build AI systems that don’t just sound smart, they actually work in production. 9+ years …

World AI Agents–35 AI Models (Claude, GPT, Llama)via One OpenAIcompatible API

Simple API proxy that gives you access to 35+ AI models (Claude Sonnet/Opus, GPT-4o, Llama, Mistral, Nova, Gemma, DeepSeek) through a single OpenAI-compatible endpoint. Drop-in replacement for the OpenAI SDK — just change base_url and api_key. - Pay once, no subscription - From €1, API key delivered instantly - Works with LangChain, LlamaIndex, any OpenAI SDK. Good price

The AI scaffolding layer is collapsing. LlamaIndex's CEO explains what survives

Show HN: Local RAG Pipeline with Weaviate and Ollama

i’ve been experimenting with building a fully local rag pipeline: weaviate for vectors + hybrid search, node.js scripts, qwen 3.5 on ollama what i found is that most of the challenges live in retrieval and chunking, not the LLM, and a good chunking strategy + the right balance in hybrid search is more effective than using a bigger and more expensive model

Data Agents with Shreya Shankar – Weaviate Podcast #135

Hey everyone! I am SUPER EXCITED to publish a new episode of the Weaviate Podcast with Shreya Shankar on Data Agents! Shreya is a Ph.D. student at UC Berkeley's EPIC Data Lab advised by Aditya Parameswaran. Her research focuses on advancing data systems and human-computer interaction! This podcast dives into her latest work on the Data Agent Benchmark! This is the first benchmark testing how well agents can perform multi-step queries across multiple database systems! We also covered DocETL and Semantic Operators, as well as how database principles can shape the future of AI agents, and why context management may be the new data management! A lot of big takeaways from this one, I hope you find it useful! YouTube: https://www.youtube.com/watch?v=C-fNVPYZrVg Spotify: https:&#x…

Ask HN: Who wants to be hired? (April 2026)

Location: Remote (Rochester, NY) Willing to relocate: No Technologies: Python, LangChain/LangGraph, RAG, Weaviate, FastAPI, React, PostgreSQL, Docker, Anthropic/OpenAI/Gemini APIs, MCP, multi-agent systems Résumé/CV: github.com/forkei Resume available on request, please send me an email. Email: olivier.couthaud@gmail.com CS/AI accelerated MS student at RIT. I build production multi-agent systems and RAG pipelines. Shipped: - Enterprise RAG pipeline (Weaviate + Oracle DB) for a finance client - VOS: open-source multi-agent virtual OS with MCP (github.com/Forkei/VOS-public) - rookery.network: live social platform with GNN paper recommendations - VibeOS: CLI-native agentic OS, faster than MCP tools (in progress) 5/5 on Wyzant, 6+ client projects. …

Weaviate Podcast on Substack

https://weaviatepodcast.substack.com/?r=82hn51&utm_campaign=...

Weaviate Podcast on Substack

If Dspy is so great, why isn't anyone using it?

Nobody uses it except for maybe the weaviate developer advocates running those jupyter cells.

Multi-Vector Search with Amélie Chatelain and Antoine Chaffin

Hey everyone! I am SUPER EXCITED to publish a new episode of the Weaviate Podcast with Amélie Chatelain and Antoine Chaffin on Multi-Vector Search! Amélie, Antoine, and the LightOn team are on fire! They are making breakthrough after breakthrough in Search with Multi-Vector, Late Interaction retrieval models. This podcast covers all sorts of topics, starting with the motivation of Multi-Vector Search to its particular successes in code with ColGrep, as well as reasoning-intensive and multimodal retrieval. We also covered the cost of MaxSim and Multi-Vector Storage and how MUVERA and PLAID can help. If that wasn't enough, the podcast concludes with their new work on ColBERT-Zero and PyLate! A lot of big takeaways from this one, I hope you find it useful! YouTube: https://www.yout…