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

Code

Full-text search across 71045 articles. Combine with topic and date filters; results sorted by relevance.

results 71045 page 1580/3553 follow RSS for this search
00:00
2026-11-04
massdriver.cloud
ai-research

Qwen3.8 2.4T-A95B on iac-bench 2026-10

Alibaba's Qwen3.8 2.4T-A95B, an open-weight model accessed via OpenRouter and priced at $2.00/$6.00 per million input/output tokens, scored an overall composite of 81.6 on the iac-bench 2026-10 infrastructure-as-code eva…

00:00
2026-11-04
massdriver.cloud
large-language-models

GPT-6.1 Sol on iac-bench 2026-10

OpenAI's GPT-6.1 Sol scored an overall composite of 87.2 on the iac-bench 2026-10 infrastructure-as-code benchmark, ranking third of 16 models with a 95% rank interval of 2–8, according to Massdriver's LLM rankings. GPT-…

13:54
2026-11-03
githubstatus.com
ai-products

Incident with API, Git, and Copilot requests

GitHub reported degraded performance across its API, Issues, and Copilot services on Nov 3, 2025, with the first public notice at 13:25 UTC stating the company was investigating reports of degraded performance for Copilo…

20:03
2026-11-02
gist.github.com
ai-safety

patch the cl0d binary

A developer published a Python script that patches the Claude Code binary (build 2.1.316) in place, replacing an embedded safety string that tells the model not to reproduce withheld content with text instructing it to j…

19:57
2026-11-02
playground.blupe.io
robotics

I made it easy to see how well robotics models acutally work

A developer built the Blupe playground, an open-source interface that lets users control real robot arms with AI models, submit task prompts, and watch live video of runs, with code published on GitHub under the blupe-re…

15:08
2026-11-01
byteiota.com
ai-products

Codex Security Cloud: 74% True Positive Rate vs. Snyk’s 28%

OpenAI's Codex Security Cloud recorded a 74% true positive rate against Snyk's 28% in independent testing, according to byteiota. The byteiota report outlines how Codex Security Cloud works, how to set it up, and which t…

21:57
2026-10-31
github.com
ai-agents

Show HN: Muse Zouroboros, gives Muse a software factory

A developer released Zouroboros, a "workshop" layer for the Muse coding assistant, published on npm in both a community version and a hosted version. Zouroboros splits long-running jobs into pieces and routes them across…

02:08
2026-10-31
byteiota.com
ai-agents

Entire: Ex-GitHub CEO Builds a Git Forge for AI Agents

Former GitHub CEO Thomas Dohmke has launched Entire, a Git forge built for AI agents that replaces pull requests with agent-run evaluation reviews called Trails. The product targets developers working with AI agents and …

01:10
2026-10-31
byteiota.com
artificial-intelligence

JetBrains Mellum2.1: From 2% to 47% on SWE-Bench

JetBrains released Mellum2.1, a 12B-parameter mixture-of-experts coding model that scores 47% on SWE-bench Verified, up from 2% for the prior version, according to byteiota. JetBrains trained Mellum2.1 with reinforcement…

23:23
2026-10-30
testingcatalog.com
ai-agents

SpaceXSI prepares Texting and Tasks hub support for Grok Bot

SpaceX AI is preparing to release Grok Bot 1.0.0, the first stable version of its autonomous AI agent, and the build is already available for download even though it has not officially rolled out to users. Code spotted i…

11:18
2026-10-30
adweek.com
ai-agents

Zocdoc Opens Its Platform to AI Agents

Zocdoc announced it has opened its platform to AI agents, letting agents integrate with Zocdoc's infrastructure to find providers, verify insurance plans, and book and add appointments to patients' calendars. Zocdoc said…

06:08
2026-10-29
dev.to
ai-agents

How to Give Cursor Accurate API Tools with an MCP Server

Powerduck published a guide showing developers how to generate an MCP server from an OpenAPI spec, run it locally, and register it in Cursor's MCP configuration so the coding agent calls typed tools tied to real API oper…

02:11
2026-10-29
byteiota.com
ai-products

GitHub Copilot Fusion Is Now GA: Cascade, Critique, Half the Cost

GitHub Copilot Fusion reached general availability at GitHub Universe 2026, introducing Single, Cascade, and Critique execution patterns for the coding assistant. The byteiota report frames the release around cost claims…

21:28
2026-10-28
blog.adafruit.com
artificial-intelligence

Can AI design a working PCB? @JLCPCB

JLCPCB highlighted on X a printed circuit board designed with the help of an AI agent working inside KiCad, built by a developer identified as John. The resulting GNSS module uses a u-blox MAX-M10S receiver, measures 25 …

15:05
2026-10-28
dev.to
ai-agents

The pre-merge checklist for AI-generated diffs

A developer published a ten-point pre-merge checklist for reviewing AI-generated code diffs, aimed at closing the review gap where agent-authored pull requests are often merged by the same person who prompted them. The c…

05:11
2026-10-28
byteiota.com
ai-tools

Entire: Ex-GitHub CEO’s New Git Forge Kills the Pull Request

Former GitHub CEO Thomas Dohmke launched Entire, a Git forge that replaces pull requests with AI-scored eval dashboards built around features called Trails and Continuous Memory, backed by a $60 million bet. The launch t…

← prev page 1580 / 3553 next →