» Tag
llm
471 postsProxy for OpenAI Codex and Claude Code: Use Any LLM with Them
Use opencodex as a universal proxy for OpenAI Codex and Claude Code with any LLM.
LLM Context Profiler: A Tool for Tracking Context Usage by Agents
ContextSpy analyzes LLM API requests to track and optimize context usage.
I Built a Simple Tool to Observe My AI Agents' Activities
Otterscope, a tool I built for monitoring small LLM agents, offers an efficient and user-friendly solution for observing agent activities.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comCan LLMs Achieve Deep Understanding of Computer Architecture Papers?
Exploring the ability of large language models to deeply understand computer architecture papers through the Gauntlet pipeline, which shows significant advantages in analysis.
LLM Evaluations for Developer Tools: Useful, Correct, Safe
How to evaluate LLM features in developer tools across correctness, usefulness, and safety.
Why DB Connections Are Not Held During Slow LLM Calls
Not holding DB connections during LLM calls enhances performance in AI systems. We explore this using the Honcho example.
Treating LLMs as Unreliable Functions for Better Engineering
Improve your software development process by treating LLMs as unreliable functions.
Choosing the Right Tool for LLM Calls: Pipeline, Flow, or Chain?
Tips for selecting the right tool between LLM calls. Discover the differences between pipeline, flow, and chain.
AI Inference Engineering: Inside the Prefill-Decode Split
A technical look at how LLM inference splits into compute-bound prefill and memory-bound decode phases, and the optimization techniques engineers use to scale them.
Reading Agent Traces Reveals What Evals Can't Decide
An agent built for AI Engineer World's Fair invented fake speakers. Reading agent traces, not evals, caught it—key lessons on model choice, cost, and observability for engineers.