Trending

Gemini 3 Flash: frontier intelligence built for speed

Why outcome-billing makes sense for AI Agents

Show HN: TheAuditor v2.0 – A ”Flight Computer“ for AI Coding Agents

Context: Odin’s Most Misunderstood Feature

AIsbom – open-source CLI to detect "Pickle Bombs" in PyTorch models

Debug Mode for LLMs in vLLora

Anthropic Outage for Opus 4.5 and Sonnet 4/4.5 across all services

I fed 24 years of my blog posts to a Markov model

No-Tifier (2017)

OpenAI at QCon AI NYC: Fine Tuning the Enterprise

At QCon AI NYC 2025, Will Hang from OpenAI unveiled Agent RFT—a cutting-edge reinforcement fine-tuning approach for tool-using agents. By optimizing prompts and tasks before model adjustments, Hang showcased effective strategies to enhance decision-making and efficiency, emphasizing a balanced grading system. The session revealed a future where smarter agents reduce latency and improve outcomes. By Andrew Hoblitzell

Podcast: Platform Engineering for AI: Scaling Agents and MCP at LinkedIn

QCon AI New York Chair Wes Reisz talks with LinkedIn’s Karthik Ramgopal and Prince Valluri about enabling AI agents at enterprise scale. They discuss how platform teams orchestrate secure, multi-agentic systems, the role of MCP, the use of foreground and background agents, improving developer experience, and reducing toil. By Karthik Ramgopal, Prince Valluri

Replit Introduces New AI Integrations for Multi-Model Development

Replit has introduced Replit AI Integrations, a feature that lets users select third-party models directly inside the IDE and automatically generate the code needed to run inference. By Daniel Dominguez

Help me price my AI agent user usage

[P] Cyreal - Yet Another Jax Dataloader

[D] What does interpretability look like?

To Mistral and other lab employees: please test with community tools BEFORE releasing models

New in llama.cpp: Live Model Switching

Built a GGUF memory & tok/sec calculator for inference requirements – Drop in any HF GGUF URL

[D] How did Gemini 3 Pro manage to get 38.3% on Humanity's Last Exam?

How to use an LLM Gateway for Request-Level Budget Enforcement

[R] [N] TabPFN now scales to millions of rows (tabular foundation model)