Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Daymond Hyper
Rebuilding the Deprecated PostgreSQL MCP Server in Rust: Safe by Default
A deprecated server with 475,790 downloads a month @modelcontextprotocol/server-postgres last shipped a version on 4 December 2024. It is marked deprecated on npm — the registry itself tells you the package is no longer supported. In the thirty days to 9 August 2026 it was downloaded 475,790 times. That gap is the whole story. This is the piece of software standing between an LLM agent and a production database, in tens of thousands of installations, and nobody is maintaining it.
[Dev Log][Python] Create short videos from photos and clips with Gemini 3.7 Flash: ReelCraft
Preface: It all started with a misunderstanding.
Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit
A paper from researchers at ELLIS Institute Tübingen, the Max Planck Institute for Intelligent Systems, and Snyk shows that the encrypted reasoning blocks Anthropic, OpenAI, and Google return to API clients are not the protection they look like. The authors replayed a reasoning block produced by a frontier model into a weaker model from the same provider, jailbroke the weaker model, and recovered the stronger model's hidden reasoning in plaintext. The whole extraction takes two API calls.
Vim-Fu
I used to take ferocious pride in my Vim skills. I knew all the hot keys, tricks and tips. I wrote macros, memorized register mappings and even dabbled in Vim script. My Vim-Fu was strong. Nowadays, my Vim skills have mostly atrophied. I rarely open a text editor and my .vimrc is outdated and sad. Times have changed. Nobody writes code by hand anymore. Instead we practically will it into existence with AI.
Five things I disabled before installing a vendor's agent runtime
Two services I connected recently both call the thing they ship a "skill". One is a hosted endpoint. The other is a zip file. The review those two need has almost nothing in common, and I do not think the word is doing anyone any favours. Luckin Coffee runs an MCP server at their own domain. My agent sends JSON-RPC over HTTPS, and their code stays on their machines. The questions there are the familiar ones. What can it see, what scopes did I grant, can it spend my money.
New Model Dropped? Run Your Own Git History Through It First
The release notes say it's faster. The launch thread says it beats everything. Three people I follow have already switched. And yet, every time I've switched on that basis alone, I've quietly switched back two weeks later after the model mangled a migration script or confidently explained a bug that didn't exist. The gap is simple: public benchmarks measure what benchmarks measure.
AI Product Builder? Is this realistic?
I recently came across a new type of role advertised in career postings, the one of an "AI Product Builder": a seasoned individual who works as a hybrid between a product manager and developer. The premise is founded on the advancement of code harnesses and the desire to reduce the idea -> ship cycle. By having a single person own the requirements, and the implementation, that person is able to iterate and experiment faster.
Testing your AI generated code like a human reviewer
Testing your AI generated code like a human reviewer The best test I know for agent written code: delete the implementation and see if the tests fail. If they still pass, they were never testing anything. Agents love writing tests that only check the code runs and not that it is right. Add one rule to your rules file. Make every test prove a behavior, not an implementation detail. That single rule has caught more broken agent code than anything else I have tried.
You do not need a big AI setup to get value
You do not need a big AI setup to get value The most useful AI workflow I have is one file. A short AGENTS.md contract that tells the agent how to behave in my repo. No framework. No prompt library. No fine tuning. Just a list of rules the agent reads before it starts. You would be surprised how much bad behavior disappears when the first thing your agent reads is a list of things you will not accept.
I Gave Claude Code an AGENTS.md Contract and Stopped Babysitting It
Claude Code follows instructions too well, and that's the whole problem. When nothing tells it what engineering discipline looks like, it invents a plausible version: graceful degradation into any, tests that assert implementation details so they pass no matter what, silent catch (e) {} blocks eating the failures you needed to hear about. I spent months working around this one edit at a time. The fix wasn't a better prompt. It was a contract.
How to make your AI coding agent stop writing slop
Every AI coding agent I've used shares one habit: it writes the plausible thing. The code compiles. The tests pass. And a senior engineer reviewing it would reach for a red pen. any where a union belongs. Tests that assert on implementation so they survive any refactor. catch (e) {} blocks that quietly swallow production errors. The fix isn't a better model or a cleverer prompt. It's a set of rules at the repo level, written in a format the agent is guaranteed to read.
Cursor Rules: How to Stop Your AI Agent From Writing Slop
You just installed Cursor, opened a TypeScript file, and asked the agent to fix a bug. Ten seconds later it handed you a type SomeType = any and a @ts-ignore above the line that wouldn't compile. This is the moment most developers discover that AI coding agents are powerful but undisciplined. The fix isn't a better model. It's rules. Most AI coding agent best practices boil down to a single idea: tell the agent what good looks like before it starts typing.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Daymond
Contact Daymond, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack