RSSAmplifier

Blog

Paika!

Backend, Data Engineering, Infrastructure, Cloud, and everything in between

paika.techRSS feed ↗10 posts

Latest posts

Trusting LLM’s with Root Access

Working on the Presidential AI mentions made it obvious to me how good LLM agents (particularly Claude Code) were at doing operations. I had the LLM do it all - I just gave it root access to an AWS account, and it created the buckets, SQS queues, ECR, ECS, all the good three letter services. Stitched them all together and I just operated the system via chat (hey add more videos to transcribe,…

Agents - Who’s to Blame?

2026 will see the industry roll out large-scale cloud agent orchestration systems at large companies. One of the biggest questions will be - how does identity (authn and authz) work? When something goes wrong, whose responsibility is it to own that failure?

Distributed S3 LLM Eval

Building on my LLM eval framework, I added a much harder test - build a three node distributed S3 cluster. The eval would run the binaries, and do chaos testing - killing nodes, recovering them, etc.

Making my own LLM Agent Eval Framwork

Recently I’ve been interested in Reinforcement Learning, particularly in evals - how do we measure language models’ effectiveness as agents?

Vibecoding Semantics

Vibecoding, as popularized by Andrej Karpathy, is a tricky word.

Future Contracts for GPU’s

Document Status: Back of the envelope math and my brainstorming.

Learning via the Theory Build Write Loop

Over the past month I’ve been doing a crash course on machine learning as I come up to speed on AI progress. In 2025 I had a child, and between the pregnancy leading up to it, a fun project at my day job, and all the dirty diapers since I have been paying a lot less attention to the field than is warranted. Claude Opus 4.5 burst this bubble - it’s now agentic enough to be a Software Engineer I or…

Multi-Agent Orchestration

With Claude Opus 4.5, coding is effectively solved. But any good developer will quickly realize the problem - agents are slow! You can watch one working, and occasionally you’ll provide input, but many times you are sitting around for 5+ minutes at a time not being productive. You can’t do something else, since you need to make sure the agent is on track.

Growing admiration for the Helix Editor

Recently I tried out the helix editor primarily because I’ve enjoyed neovim but found the lua plugin system annoying, and helix is written in Rust (my favorite language).

Training an LLM in WASM from scratch

Try the demo here