» Tag
llm
536 postsScaling Laws Explained: From Kaplan to Chinchilla to Overtraining
A breakdown of LLM scaling laws from Kaplan to Chinchilla, and why modern models are deliberately overtrained to cut inference costs.
Why Multi-Model AI Pipelines Lose the Truth at Handoffs
Model handoffs in multi-agent AI systems can silently erase caveats and evidence, turning careful findings into false certainty without errors.
Clare Liguori on AWS Strands SDK's Model-Driven Agent Design
AWS engineer Clare Liguori explains the model-driven design behind the Strands Agents SDK and lessons from building production AI agents.
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.comBack-End Engineering in 2026: APIs Give Way to Agent Orchestration
Back-end engineering in 2026 shifts from stateless APIs to agentic systems: orchestration, async tasks, tool governance, and reasoning traces.
Stop Fine-Tuning Everything: A Framework for Model Adaptation
A decision framework for choosing between prompt engineering, RAG, fine-tuning, and domain pre-training when adapting foundation models.
How AI Pinpointed the Root Cause of a Multi-Region K8s Outage
How Trendyol used an LLM to trace a multi-region Kubernetes outage to a systemd upgrade bug in under an hour, sifting 200MB of logs.
Belay: a local firewall for AI coding agents
Belay is an open-source, local-first security layer that gates AI coding agent tool calls, blocking secret leaks and destructive commands in real time.
freeq ties AI model spend to identity, not shared API keys
freeq extends its DID-based protocol to gate AI model spend by identity, letting agents borrow bounded capacity without sharing API keys.
AI Doesn't Replace Architecture — It Makes It More Valuable
AI made code generation cheap, but not the architectural decisions behind it. Why the bottleneck shifted from typing to deciding for engineers.
Speculative Decoding: The Free Speedup Most Local LLM Setups Skip
Speculative decoding speeds up local LLM inference 1.5-2.5x with identical output; 2026 saw it built into models via multi-token prediction.