» Tag
llm
472 postsAssessing LLM Inference Profitability: Insights from Kimi K3
Analysis and calculations on the profitability of LLM inference using Kimi K3.
Comparing LLM Evaluation Frameworks: Measuring Model Performance
Learn to evaluate LLM applications with RAGAS, DeepEval, and Promptfoo. Address biases effectively in your designs.
Introduction to LLM Inference: Process and Its Importance
Explore the LLM inference process and its significance in engineering. Gain insights into performance and model structure.
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.comI Trained a 30M-Parameter LLM from Scratch: The Scaling "Floor" Was a Mirage
A 30M parameter language model was trained from scratch, aiming to deepen understanding of transformers.
PoPE: Evaluating Error-Conditioned Self-Repair in Small Code LLMs
PoPE introduces a new standard for evaluating self-repair in small code LLMs, emphasizing rigorous placebo-controlled assessments.
Yes-Brainer: A Council of LLMs Debating in the Browser
Yes-Brainer enables better outcomes by facilitating debates among AI models for complex decisions.
Reducing LLM Costs with Prompt Caching, Batches API, and Model Routing
Explore methods to reduce LLM costs for the Claude API: prompt caching, Batches API, and model routing.
The Audience of One Problem: Trusting Your AI Visibility Test
Explore the pitfalls of testing your AI visibility from your own session. Learn how to create a clean testing environment.
Finetuning a Reasoning LLM with Supervised or Reinforcement Learning?
Critical insights on training data representation and loss management in LLM finetuning.
Harness Engineering for Coding Agent Users
A framework for harnessing coding agents: feedforward guides, feedback sensors, and computational vs inferential controls across the development lifecycle.