ToolingFlexAI·82d ago·3 min read
How to Evaluate an Inference Provider: 5 Checks to RunFlexAI provides five checks for evaluating inference providers.
News Hub
What actually shipped in agent engineering, pulled from the labs, arXiv and Hacker News.
See who we follow8 articles
Open sourceFlexAI·84d ago·3 min read
Best Open-Source LLM for Function Calling: 5 ChecksFlexAI identifies five checks for selecting open-source LLMs with function calling capability.
Open sourceFlexAI·130d ago·3 min read
Open Source vs Closed LLMs: When to SwitchArticle discusses when to switch between open source and closed LLMs.
ToolingFlexAI·134d ago·3 min read
EasyR1 RL Fine-Tuning: GRPO vs DAPOEasyR1 RL fine-tuning compares GRPO versus DAPO methods.
ResearchFlexAI·148d ago·3 min read
How to Benchmark Open-Source ModelsArticle about methods for benchmarking open-source language models.
ToolingFlexAI·154d ago·3 min read
32B Legal LLM Beats Frontier at 4× Lower CostA 32 billion parameter legal language model achieves frontier performance at four times lower cost.
ToolingFlexAI·161d ago·3 min read
LLM Inference GPU Sizing: Pick the Right GPUArticle about selecting appropriate GPUs for language model inference workloads.
ResearchFlexAI·175d ago·3 min read
FlexBench: Open-Source MLPerf LLM Inference BenchmarkFlexAI released FlexBench, an open-source MLPerf LLM inference benchmark.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.