Tag feed

#developer-tools

3,113 posts623 followers

Explore Hashnode

Alternatives

Trending tags this week

DMDaisuke Masudadaisuke.masuda.tokyo3h ago · 19 min read

Where Is JetBrains AI Heading?

AI coding tools are usually compared as if they were interchangeable chat boxes: Which model scores higher? Which agent edits more files? Which subscription is cheaper? JetBrains appears to be asking

0

EMEwan Makdeveloper.tenten.co2h ago · 8 min read

A Spotify Engineer Routed Claude Code's I/O to a Small Model—and Cut Tokens 90%

The most expensive part of Claude Code may not be reasoning. Spotify engineer Dimitri Mazmanov found that a large share of tokens went to reading files, copying test patterns, and generating boilerpla

0

RRulestackrulestack.hashnode.dev16h ago · 8 min read

The 404 only we could see: 23.8 hours inside a cache entry we made ourselves

For 23.8 hours, one of our published articles returned 404 to us and 200 to everyone else. The article was fine. Our request path had been poisoned — by a request we made ourselves, before the article

0

RRulestackrulestack.hashnode.dev1d ago · 8 min read

Documentation, audit, or commit gate: three postures for CLAUDE.md and AGENTS.md — and where each one stops

A reader asked, at the end of an unusually good comment on one of our CLAUDE.md posts: "The bigger question for me is: should agent instruction files eventually be treated less like documentation and

0

YGYusuf Gundogdulibredb.hashnode.dev1d ago · 8 min read

Trino breaks the metadata assumptions a database IDE is built on

A note on transparency: I work on LibreDB Studio, an open source (MIT) database IDE. This post is about a design problem we hit while adding Trino support, not a pitch. The lesson generalizes to any c

1

C

NPNirdesh pokharelblog.nirdeshpokhrel.com.np3d ago · 5 min read

digit-to-words-nepali: Converting Numbers to Nepali Words, Properly

If you've ever built a billing system, an invoice generator, or a cheque-printing tool for a Nepali audience, you already know the pain: turning 1234 into "एक हजार दुई सय चौँतिस" is not a simple looku

0

RPRudrendu Paulfreecodecamp.org2d ago · 40 min read

Agentic AI Engineering in Practice: How AI Engineers and Forward-Deployed Engineers Build with Claude Code, Codex, and Gemini

A practical, three-tool guide to the AI-native software development life cycle (SDLC): Plan, Design, Build, Test, Deploy, Maintain, reimagined for agentic coding. In March 2025, a small nonprofit rese

0

CCopperSunDevbrasscoders.hashnode.dev2d ago · 8 min read

AI Code License Risk From Training-Data Memorization

Your AI coding assistant did not write that function from scratch. It predicted the next token, and the token before that, from a model trained on a large slice of public code. Most of the time the re

0

RRulestackrulestack.hashnode.dev2d ago · 8 min read

Quote 13.3%, reply 10.1%, like 2.6% — and the repost code we deleted

Three ways to touch a stranger's post on Bluesky, three follow-back rates, measured against the same follower roster: First touch Follow-back Mature cohort Quote post 13.3% 2 of 15 Reply + lik

0

RRulestackrulestack.hashnode.dev2d ago · 7 min read

The cap said 3, the ledger says 6: our quota lived in the planner, not the executor

One of our product levers is capped at three executions per ISO week. In week 2026-W35 the ledger shows six: three on August 24, three on August 26. Nothing crashed, no alert fired, and every one of t

0

#developer-tools

Search Hashnode

#developer-tools

Explore Hashnode

Trending tags this week

Where Is JetBrains AI Heading?

A Spotify Engineer Routed Claude Code's I/O to a Small Model—and Cut Tokens 90%

The 404 only we could see: 23.8 hours inside a cache entry we made ourselves

Documentation, audit, or commit gate: three postures for CLAUDE.md and AGENTS.md — and where each one stops

Trino breaks the metadata assumptions a database IDE is built on

digit-to-words-nepali: Converting Numbers to Nepali Words, Properly

Agentic AI Engineering in Practice: How AI Engineers and Forward-Deployed Engineers Build with Claude Code, Codex, and Gemini

AI Code License Risk From Training-Data Memorization

Quote 13.3%, reply 10.1%, like 2.6% — and the repost code we deleted

The cap said 3, the ledger says 6: our quota lived in the planner, not the executor