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

Code

Full-text search across 65924 articles. Combine with topic and date filters; results sorted by relevance.

results 65924 page 723/3297 follow RSS for this search
12:48
2026-07-23
promptcube3.com
developer-tools

Moxie Docs: Automating Developer Knowledgebases

Moxie Docs automates developer knowledgebases by structuring technical specifications for both human readability and AI ingestibility, streamlining workflows for teams building custom GPTs or coding assistants. The tool …

10:07
2026-07-23
testingcatalog.com
artificial-intelligence

OpenAI tests Codex Realtime Voice Mode for ChatGPT

OpenAI is building a real-time voice mode for Codex that extends beyond code into a general-purpose agentic assistant, according to code strings and supporting functionality found in the ChatGPT bundle. The system prompt…

16:21
2026-07-22
github.blog
developer-tools

New Copilot usage metrics impact dashboard

GitHub released a new Copilot usage metrics impact dashboard for enterprise administrators and organization owners, grouping engaged users by AI adoption phase (Phase 1 Code-first, Phase 2 Agent-first, Phase 3 Multi-agen…

00:00
2026-07-21
blog.exe.dev
ai-agents

Customizing Shelley, Customizing Software

Exe.dev's coding agent Shelley can be customized by asking it to change itself, with customizations rebased onto each new version. The company advocates editing code directly as a third way to customize software, treatin…

20:15
2026-07-20
varonis.com
ai-safety

A Look Inside the HuggingFace Breach

On July 16, 2026, HuggingFace disclosed a security breach in which an autonomous AI attacker infiltrated its internal infrastructure by chaining two remote code execution vulnerabilities in its dataset processing pipelin…

17:43
2026-07-20
aac.social
artificial-intelligence

Agents' skills are too long (mine were too)

Anthropic cut Claude Code's system prompt by about 80% as models get smarter, according to Thariq of the Claude Code team in an interview with Peter Yang. The author built skillmin, a skill minimizer that uses evals to s…

15:19
2026-07-20
fortran-lang.discourse.group
developer-tools

C to Fortran transpiler

A developer used AI models Codex and Claude to create a Python-based transpiler that converts C code to modern Fortran, successfully translating several numerical C programs. The tool is being tested on larger code bases…

14:32
2026-07-20
helpnetsecurity.com
artificial-intelligence

ServiceNow pre-auth RCE exploited in the wild (CVE-2026-6875)

Attackers are actively exploiting CVE-2026-6875, a critical pre-authentication remote code execution vulnerability in the ServiceNow AI Platform, according to threat intelligence firm Defused. The flaw, discovered by Sea…

16:02
2026-07-19
twitter.com
artificial-intelligence

Moonshot AI suspends new subscriptions due to Kimi K3 demand

Moonshot AI has temporarily suspended new subscriptions for its Kimi K3 service due to overwhelming demand that pushed GPU capacity to its limits over the past 48 hours, the company announced. Existing subscribers are un…

19:37
2026-07-17
dev.to
ai-agents

Building AI Agents in PHP: Tool Calling with Laravel

A developer detailed a pattern for building AI agents in PHP using Laravel, implementing tool calling to enable chatbots to query databases and services. The approach uses a loop where the model selects a tool, the code …

19:13
2026-07-17
news.ycombinator.com
ai-agents

Show HN: Run Hermes Agent with Kimi 3 in a sandbox

Hermes Agents running on the Kimi K3 model are now available inside a sandbox, allowing users to deploy the agent without a Mac mini and connect it to Telegram in under 10 minutes. The setup requires creating a Telegram …

03:41
2026-07-17
lowlatencyclub.ai
ai-tools

AI Assistant Needs a Back End. Put It at the Edge

Telnyx has published a guide and open-source Go code demonstrating how to build a production backend for a voice AI assistant using a single Edge Compute function, handling both dynamic variables and webhook tool calls w…

11:26
2026-07-16
thestack.technology
ai-tools

Cursor says seven-month unresolved bug is not its responsibility

Cursor, a vibe coding platform owned by Anysphere and acquired by SpaceX for $60 billion in June, has denied responsibility for an arbitrary code execution bug that researchers at Mindgard say went unpatched for seven mo…

07:05
2026-07-16
twitter.com
ai-safety

Can we trust open weight models?

A researcher demonstrated that an open-weight coding model can be turned into a backdoor in under one hour and for less than $100, raising concerns about trust in Chinese open weight models like GLM 5.2, which scored wel…

← prev page 723 / 3297 next →