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

Code

Full-text search across 68265 articles. Combine with topic and date filters; results sorted by relevance.

results 68265 page 953/3414 follow RSS for this search
08:29
2026-10-05
aihero.dev
ai-agents

The /pr Skill

Developer Matt Pocock released a new coding-agent skill called /pr, installable via `npx skills@latest add mattpocock/skills --skill=pr`, that defines the shape of a pull request body as three sections: Summary, Evidence…

07:31
2026-10-05
vercel.com
ai-products

What Is Perplexity's Decisions API?

Perplexity released the Decisions API, which evaluates supplied content and returns typed predictions with probabilities using its pplx-decider-v1-27b model that accepts text and images. The API separates evidence in a s…

02:34
2026-10-05
dev.to
ai-products

Data Structure Mate cutey

A developer built AI Mate, an AI-powered study buddy for learning data structures and algorithms that guides students from brute-force solutions to optimal ones step by step rather than handing over finished code. The to…

15:04
2026-10-04
dev.to
ai-infrastructure

When Gemini Rejects Cloudflare Workers by Location

A developer debugging a scheduled Cloudflare Workers integration with the Gemini API found that a single incident window contained two distinct failure modes: transient HTTP 503 capacity errors that clear with exponentia…

12:29
2026-10-04
dev.to
ai-agents

I A/B-tested 9 popular AI agent skills. 4 of them did nothing.

A developer A/B-tested nine popular AI coding-agent skills against Sonnet 5.5 and Haiku 4.5 using Anthropic's claude plugin eval, running 19 test cases three times per arm, and found four of the nine added nothing. Workf…

08:47
2026-10-03
tej.as
large-language-models

Aleph Alpha Kolibri: How the Sovereign German LLM Works

Aleph Alpha released Kolibri, an open-weight German-and-English large language model with 78.1 billion total parameters that activates 3.46 billion per token, on 3 October 2026 under the Apache 2.0 license, with weights …

20:39
2026-10-02
superml.dev
ai-agents

Fail-Plausible: When Agents Turn Errors Into Fiction

A June 2026 paper, "When Errors Become Narratives" by Wei Wu, documented 22 incidents over eight weeks in which a single production agent runtime turned error signals into fluent, plausible answers instead of surfacing f…

06:40
2026-10-02
latent.space
ai-agents

[AINews] Pi 1.0, Pi Durable, and AIE NYC

Earendil released Pi 1.0 and Pi Durable, both of which reached the front page of Hacker News, with Pi Durable porting Pi to TypeScript and externalizing all stateful components so agents resume from their last exact chec…

04:32
2026-10-02
dev.to
ai-tools

A Working Beta in 72 Hours — A Record of How Tessvia Was Born

A developer handed a full MVP specification to Claude Code on June 10, 2026, and within 72 hours produced a working beta of Tessvia — an 11-package Turborepo monorepo with a Chrome extension and CLI, all 15 CLI smoke tes…

13:09
2026-10-01
dev.to
ai-agents

Context Over MCP, Part VI: Context You Can See

A developer released mcp-context-card, an MIT-licensed MCP server that renders a project's agent context — AGENTS.md sections, memory facts and their file locations — as a visible HTML "context card" so developers can in…

12:42
2026-10-01
blog.jetbrains.com
ai-agents

A New Agentic Experience: JetBrains Air in IDEs – EAP Now Open

JetBrains launched the Early Access Program for JetBrains Air in its IDEs, available now as a plugin on the JetBrains Marketplace and natively in the 2026.3 EAP builds. Air is an open system for agentic development that …

12:40
2026-10-01
aikido.dev
ai-agents

Top endpoint security tools for developers in 2026

Aikido Security's Device Protection tool blocks malicious installs across packages, IDE and browser extensions, and AI tools using a default 48-hour package-age hold, according to the company's comparison of endpoint sec…

10:24
2026-10-01
byteiota.com
ai-infrastructure

Magnitude: The Local Inference Engine That Tunes Itself

Magnitude (YC S25) released v0.2.0 on August 5, 2026, replacing its llama.cpp backend with a Rust inference engine that auto-tunes GPU kernels on the user's specific chip, lifting Qwen 3.6 35B decode from 30 to 57 tokens…

01:11
2026-10-01
dev.to
ai-agents

Plain Japanese in, ComfyUI workflow out

Japanese AI practitioners are increasingly embedding models inside existing tools rather than chatting with them, according to a weekly roundup of posts on X. Developers shinshin86 and rotejin used Claude Code to generat…

← prev page 953 / 3414 next →