Email Verification Logs Need a Privacy Contract
Email verification is usually discussed as a delivery problem: did the message arrive, did the link work, and did the user finish signup? In product…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
- игры
AI
News
Tech
agents
ai
api
architecture
automation
backend
beginners
career
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Your MCP Hub Exposes Every Tool to Every Agent. That's the Bug.
We stood up an internal MCP hub last quarter. It aggregated four services behind one endpoint, listed every tool in a single catalog, and let any co…
Pin baseUrl in the Gateway, Not in the Agent's Prompt
The other day an agent I was testing kept hitting production. Not on purpose, not because it was being clever. It was reading the OpenAPI spec we ha…
Drift Checks in TDK CLI: Fail Fast, Generator Changes, and Catching Hand Edits Before Commit
A drift check answers one question: has someone changed a generated file by hand? TDK runs that check before Tilt starts, so a hand edit stops the s…
Building a Rust CLI With clap: Arguments, Errors, and Help That Works
A command-line tool lives or dies on its arguments. A flag that silently ignores bad input, a help screen that does not match the code, or an error…
A mental health feature for people who work with agents
It's late. The review agent has found one more thing: a boundary case in a regex. The coding agent fixes it, opens another PR, and the reviewer find…
The Portability Audit Take-Home: Grade Environment Assumptions, Not Features
A take-home that runs on the reviewer's laptop grades features; a take-home that runs anywhere grades engineering discipline. The task below asks a…
Hermes Agent v0.22.0 The Threshold Release คืออะไร? รุ่นใหญ่ที่สุดของ AI agent ที่โค้ดหดลง 34%
Hermes Agent v0.22.0 The Threshold Release คืออะไร? รุ่นใหญ่ที่สุดของ AI agent ที่โค้ดหดลง 34% โดย Nokka (นก-กา) | 17 ตุลาคม 2026 บทความนี้เขียนโดย…
Properties Without Witnesses Are Decorations: A Falsifiability Gate for Agent Patches
A property that passes on the patched tree and on the pre-patch tree carries no information. That is the first thing to measure, before you trust an…
Every regex is written once and read a hundred times. Optimize for the readers.
Somewhere in a codebase you own there's a regex that three people can write and nobody can read. Mine was a date-validation pattern — forty-some cha…
DevOps Email Tests Need a Handoff Contract
DevOps Email Tests Need a Handoff Contract Email tests in CI often fail at the boundary between two jobs: one job creates a disposable inbox, anothe…
Harvard's field data on coding agents: +30% code, +49% review time, flat output
A 78-page job market paper landed last week that puts field numbers on the argument everyone has been having from vibes. Fiona Chen and James Stratt…
Claude Code /compact vs /clear: what actually happens to your context
/compact replaces your conversation with a summary Claude writes and keeps the same session going. /clear starts a new conversation with an empty co…
How Claude Plugins Official Addresses Plugin Quality in AI Development
Objective Technical Assessment The Claude Plugins Official repository addresses a critical need in the AI development community: ensuring that the p…
The Bug Is in the Files: Characterize Filesystem Side Effects Before a Messy Refactor
Conclusion first: in a messy repo, the refactor usually breaks files, not stdout. Teams write golden tests for console output. Almost nobody asserts…
Fetch для QA: как тестировать API прямо в DevTools, не открывая Postman
Недавно у меня была итерация тестирования. Задача — проверить функционал, для которого нужно было создать 50+ сущностей. Однотипных,…
Python GA on Vercel, New Reasoning Models, and Layout-Aware Diffusion: Issue #110
This week's releases cluster around a clear theme: reducing the infrastructure surface area developers have to manage. Vercel made a serious push to…
Decide Where the Agent Runs With a Four-Axis Fit Ledger
Every week brings another round of confident model announcements, and every week my review queue looks roughly the same as it did a month earlier. T…
11 MCP Servers That Prove MCP Isn't Dead
Disclosure: I'm the founder of PDFHaul, which is #5 on this list. Originally published on the PDFHaul blog , where the full source list with links l…
48-Hour Field Notes: My Sandbox Said PASS, and Zero Tests Had Run
I spent 48 hours letting a free model generate fixes I never applied, and the most useful thing I learned was that my harness was the bug. The sandb…
Measure the Executable Share of a Docs Page Before Letting a Model Draft It
Liquid syntax error: Unknown tag 'endraw'
Which of your rule files the reviewer actually reads
Every AI review tool claims it reads your AGENTS.md or CLAUDE.md. What decides whether your standards actually land is which rule wins when two appl…
Why Google Put a Runtime Monitor on Gemini 4 Argon
Google DeepMind launched Gemini 4 Argon this week. The headline numbers look like typical frontier model marketing: top rank on the Vals Index, a 1M…
From "this is broken" to a fix PR I merge by hand
Sentry starts from what the code threw. Mushi starts from what the user felt. This is the post I wanted to read before I built Mushi. My Sentry dash…
One MCP config for Claude Code, OpenCode and OMP
Three files for one server You use Claude Code for one task and OpenCode for another, and both should see the same Figma and Linear MCP servers. Eac…
Inject a budget line into every Claude Code prompt with UserPromptSubmit
Hooks are not only for blocking bad tool calls. UserPromptSubmit runs when you send a message, before the model sees it — so you can inject a short…
Startup credits are a moving target — here's how to verify them against an open registry
Every founder eventually collects a folder of "startup credits" links: cloud credits, API allowances, free tiers that scale. The problem is that the…
Six dev.to Articles Walked In, Four Roadmap Phases Walked Out: Why the Community Is the Best Design Review Your Project Will Ever Get
One evening of reading other people's posts about agentic coding turned into three new global rules on my machine, four new phases on cairn's roadma…
The artifact worth reviewing when agents write the code
GitHub's Security Lab reported 24 Android vulnerabilities found by an AI security agent, and the part worth copying is what ended up version-control…
An input changes mid-run: what four task tools do
A cache key describes a task's inputs at one moment. If an input changes while the command runs, the output may have been built from bytes the key d…