grep -r "Code" /news · home›search
grep -rli "Code" /news

Code

Full-text search across 68710 articles. Combine with topic and date filters; results sorted by relevance.

results 68710 page 1139/3436 follow RSS for this search
16:06
2026-10-04
fortran-lang.discourse.group
developer-tools

An AI case study: qdldl-fortran

Developer Jacob Williams used Claude Opus 5.5 to port the QDLDL sparse linear algebra C library to Fortran, publishing the result as qdldl-fortran on GitHub. The AI wrote the Fortran conversion and unit tests validating …

15:31
2026-10-04
dev.to
artificial-intelligence

DatePilot A little more together

A developer built DatePilot, a full-stack private AI date planner for couples that combines a deterministic Python planner with an open-weight Gemma model served through Ollama. The app, built with React, Vite, Tailwind,…

12:52
2026-10-04
github.com
ai-tools

Herbarium – keep and review the HTML pages AI tools generate

Herbarium, a desktop reader for HTML pages generated by AI tools, has launched with Linux x86_64 and arm64 installs via a curl script plus unsigned macOS and Windows builds on its GitHub releases page. The Tauri 2, Rust,…

11:00
2026-10-04
hackaday.com
large-language-models

AI on Your Gaming PC

The open-source project Strata, from developer Niko1221, runs a 125-billion-parameter Qwen3.8 mixture-of-experts LLM on gaming-PC hardware by treating VRAM as a cache and keeping the full expert set in system RAM. Accord…

06:27
2026-10-04
dev.to
ai-tools

🔒 FocusLock AI — An AI-Powered Study Focus Planner

A developer built FocusLock AI, an open-source study productivity tool that pairs Google's open-weight Gemma model with a focus timer to generate personalized study plans. Users enter a goal and duration, and the model r…

06:02
2026-10-04
dev.to
ai-agents

Your cache hit rate is lying to you. It's the caller mix.

A developer's analysis of Claude Code prompt caching shows that account-level cache hit rates mask wildly different behavior across callers, with one deployment reporting 77% overall but roughly 0% for cron tasks that re…

01:46
2026-10-04
gist.github.com
ai-agents

GitHub Copilot reply — best way to build hermes, expert tools,

A developer outlined a blueprint for "Hermes," an operations copilot built on GitHub Copilot for a wood-interior design and fabrication studio, designed to convert customer inquiries into checked project briefs and reply…

22:53
2026-10-03
dev.to
ai-agents

Introduction to Kiro Workflows

Kiro has introduced Kiro Workflows, a feature that lets users orchestrate multiple agents through a structured, declarative JSON or YAML graph of ordered steps, parallel branches, and conditional loops. The Kiro Runtime …

04:58
2026-10-03
dev.to
ai-tools

Stop Comparing Model Prices. Measure Cost per Completed Work.

A developer argues that comparing AI model prices by token cost is misleading and proposes measuring "accepted work cost" — total task cost (model tokens, tool fees, retries, and human review) divided by the number of ac…

04:36
2026-10-03
stork.ai
ai-agents

The GitHub Screenshot Leak Agents Made Worse

Glow's research found that AI coding agents leaked more than 13,000 internal images across 900+ repositories and 343 organizations by autonomously creating public GitHub repositories to host screenshots requested for pul…

17:04
2026-10-02
gist.github.com
developer-tools

YSH Terminal v8.1.4

A developer released YSH Terminal v8.1.4, a Java Swing-based command-line emulator that implements an in-memory file and folder system, a note-taking subsystem, LAN chat and file sharing over sockets with multi-client su…

← prev page 1139 / 3436 next →