🌍 Dev.to

Building a Production AI Agent in Spring Boot: A/B Testing Prompts With an LLM Judge (Part 9)

Last week I changed a system prompt based on a feeling. It was the first prompt change after the evaluation harness from Part 8 went live, and I was completely sure about it. The target was the markdown table. Part 8's first nightly run caught the agent answering price comparisons with a markdown table that renders broken in the chat frontend. The fix looked obvious: add one line to the system prompt demanding plain text. I checked six conversations by hand. All six looked better. I was ready...
🌍 Dev.to

Your axe run is green and your dark mode has 1.04:1 contrast

I shipped a page that reported zero axe violations . It had button text at a contrast ratio of 1.04:1 β€” which is, for practical purposes, invisible text. The scan wasn't broken. It was answering a narrower question than I thought I was asking. The bug I had a theme system built the ordinary way. Tokens on :root , overridden in a prefers-color-scheme media query, and overridden again by an explicit [data-theme] attribute so a manual toggle wins in both directions. Bu...
🌍 Dev.to

Your Prompt Engineering Is Not the Bottleneck Anymore

I spend a lot of time in the AI space -- reading papers, building things, talking to engineers who are actually shipping. And there is a gap between what the demos show and what production systems actually look like that nobody is being fully honest about. So here is my honest take on where things actually are. The Problem With How We Talk About AI Agents Everyone is calling everything an "agent" right now. A function that calls a tool? Agent. A chatbot with memory? Agent. ...
🌍 Dev.to

The Security Gap in MCP Tool Servers (And What I Built to Fix It)

MCP (Model Context Protocol) is how AI agents connect to tools. Claude Desktop uses it, Cursor uses it, and thousands of developers are building MCP servers to give AI access to their APIs, databases, and infrastructure. There's one problem: MCP has no security model. The protocol defines how a client talks to a server, but says nothing about what that server is allowed to do. No authentication between client and server. No authorization on which tools can be called. No audit trail of wh...
🌍 Dev.to

The Stale Godot Class Cache Bug That Passed CI but Broke Local Startup

This is a submission for DEV's Summer Bug Smash: Clear the Lineup powered by Sentry . Project overview Nocturne Vania is a small pixel-art Metroidvania built with Godot 4. The game has interconnected rooms, enemy AI, save data, unlockable movement abilities, and a growing automated test suite. I hit this bug after adding a bell tower area. The new rooms, enemies, effects, and map markers used GDScript's class_name keyword so they could be referenced as global types. T...
🌍 Dev.to

My Commit-Message Script Has 8 Assertions in --selftest. None of Them Touch the Code That Can Actually Fail.

I have three files in this repo that shell out to something over the network or a subprocess and can fail in interesting ways: publish_devto.py , server.py , and git_commit.py . Two of them have --selftest blocks that stub the risky call and exercise the actual failure branches. One doesn't, and I only noticed because I went looking for a reason to be suspicious of my own test coverage after seeing a trending post about counting assertions in a test suite and not liking what you find. g...
🌍 Dev.to

Debugging is also clicking πŸ–±οΈ

In the last couple of posts I let agents debug over DAP β€” breakpoints, step over, continue. That's real debugging. But it's only half of it. When I debug something for real, I also click : I press the button and watch what happens, read the dialog, notice the toggle is greyed out. No backtrace ever tells you the Save button never enabled. So β€” can the agent do that half too? The web is the easy case Browsers are automatable by design. Most agent tools ship their own brow...
HackerNews

Cool URIs Don't Change (1998)

Article URL: https://www.w3.org/Provider/Style/URI Comments URL: https://news.ycombinator.com/item?id=49231809 Points: 204 # Comments: 48
HackerNews

Taxi drivers rarely die of Alzheimer's

Article URL: https://theconversation.com/taxi-drivers-rarely-die-of-alzheimers-how-complex-mental-maps-and-spatial-reasoning-protect-your-brain-286650 Comments URL: https://news.ycombinator.com/item?id=49232253 Points: 215 # Comments: 161
HackerNews

Ask HN: What are you working on? (August 2026)

What are you working on? What have you been curious about lately? Comments URL: https://news.ycombinator.com/item?id=49233423 Points: 197 # Comments: 707
HackerNews

How I use LLMs to learn complex topics

Article URL: https://laurentiugabriel.github.io/blog/articles/how-i-use-llms-to-learn/ Comments URL: https://news.ycombinator.com/item?id=49234675 Points: 488 # Comments: 274
HackerNews

The Hacker's Renaissance (2025)

Article URL: https://phrack.org/issues/72/19#article Comments URL: https://news.ycombinator.com/item?id=49235378 Points: 105 # Comments: 77
HackerNews

Tuxedo No. 2 – Cocktail recipes

Article URL: https://tuxedono2.com Comments URL: https://news.ycombinator.com/item?id=49235697 Points: 64 # Comments: 14
HackerNews

The Ambition Project

Article URL: https://www.betonit.ai/p/the-ambition-project Comments URL: https://news.ycombinator.com/item?id=49237407 Points: 14 # Comments: 1
HackerNews

Japanese court overturns Red RAW video patent

Article URL: https://www.dpreview.com/news/panasonic-did-what-apple-sony-and-nikon-couldnt-overturn-a-red-raw-video-patent/ Comments URL: https://news.ycombinator.com/item?id=49237873 Points: 63 # Comments: 10
HackerNews

How We Pushed CDC into Postgres

Article URL: https://www.snowflake.com/en/blog/engineering/postgres-to-snowflake-replication-mirroring/ Comments URL: https://news.ycombinator.com/item?id=49238050 Points: 44 # Comments: 6
HackerNews

What Happened to HackerOne?

Article URL: https://blog.teknogeek.io/posts/what-happened-to-hackerone/ Comments URL: https://news.ycombinator.com/item?id=49238561 Points: 74 # Comments: 22