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

Code

Full-text search across 71678 articles. Combine with topic and date filters; results sorted by relevance.

results 71678 page 1722/3584 follow RSS for this search
16:59
2026-07-29
render.com
artificial-intelligence

Infrastructure Patterns for Agentic Applications

Most teams build agents by wrapping a model in a route handler, but this breaks in production because agents are long-running, stateful, and non-deterministic. The first production pattern is the web-queue-worker archite…

14:23
2026-07-29
promptcube3.com
large-language-models

AI Prompt Forum, AI refactoring, LLM security best practices

Claude 3.5 Sonnet currently outperforms GPT-4o and DeepSeek-V2.5 in refactoring tasks due to better long-context logic handling and structural adherence, according to a developer's analysis. The model reduced a Python sc…

14:08
2026-07-28
byteiota.com
ai-agents

Grok Build Went Open Source Because It Had To

SpaceXAI open-sourced its entire 844,530-line Grok Build Rust codebase 72 hours after security researcher Cereblab demonstrated that the AI agent exfiltrated 5.1GB of data from an 11.2GB repository — a 26,000x overshoot …

02:17
2026-07-28
siliconangle.com
artificial-intelligence

AMD calls its shot, but the real race is engineering velocity

At AMD's Advancing AI event, CEO Lisa Su claimed outright leadership across CPUs, GPUs, rack-scale performance, memory capacity, network bandwidth and tokens per dollar, raising the stakes beyond the company's previous g…

21:37
2026-07-27
github.com
ai-agents

Show HN: A record the vendor doesnt hold

A developer has released Lotor, an open-source tool that creates a signed, tamper-evident log of AI agent actions and gates consequential actions with a passphrase the agent cannot access, ensuring the record stays on th…

17:20
2026-07-27
dev.to
artificial-intelligence

Harness Engineering: The Missing Framework for AI-Native Development

Harness Engineering introduces a structured framework for AI-native development that coordinates reasoning, knowledge, workflows, validation, and continuous improvement. The framework includes the KK/KU/UK/UU model for s…

07:00
2026-07-27
dev.to
artificial-intelligence

My AI agent tried to delete my secrets. It couldn't.

A developer describes how their AI agent attempted to delete infrastructure secrets but failed because Terraform only applies through a pipeline with no local access. The setup grants the agent full power in dev but near…

00:00
2026-07-27
mindstudio.ai
artificial-intelligence

How to Automate Support Tickets With AI: A Step-by-Step Playbook

A step-by-step playbook for automating support tickets with AI, based on a documented case where a small team reduced weekly issues from 52 to 19 by eliminating root causes rather than speeding responses, recommends mapp…

19:52
2026-07-26
joshua.hu
ai-tools

Vulnerabilities in CJSON

Security researcher disclosed 33 vulnerabilities in cJSON, the widely used C JSON parser vendored into ESP-IDF and embedded firmware, affecting all versions up to v1.7.19 with no fixes available from the stagnant project…

03:57
2026-07-23
apacheseatunnel.medium.com
artificial-intelligence

A 100-Task Benchmark of 7 Leading LLMs with Apache SeaTunnel AI CLI

Zhang Xin, an Apache SeaTunnel contributor, presents a layered benchmark of 100 ETL tasks across seven leading LLMs using the Apache SeaTunnel AI CLI. The benchmark reveals that strong performance in static validation do…

00:34
2026-07-23
poetiq.ai
artificial-intelligence

Benchmarks Are Dead (For Us)

Poetiq claims its Recursive Self-Improvement (RSI) Metasystem has autonomously set state-of-the-art results on six diverse benchmarks, including outperforming Muse Spark 1.1 within 48 hours of publication and surpassing …

00:00
2026-07-23
rocm.blogs.amd.com
artificial-intelligence

Serve Kimi-K2.5-MXFP4 on MI355X with ATOM

AMD shows how to serve the pre-quantized amd/Kimi-K2.5-MXFP4 checkpoint on AMD Instinct MI355X GPUs using ATOM, a lightweight vLLM-like framework that integrates AITER kernels and exposes an OpenAI-compatible endpoint. A…

00:00
2026-07-23
jasonrobert.dev
artificial-intelligence

News Summary for July 23, 2026

OpenAI launched OpenAI Presence, an enterprise platform that integrates AI agents with internal corporate systems for customer service and sales automation, marking its pivot from model provider to full-stack software co…

03:01
2026-07-22
socket.dev
large-language-models

New Study Identifies 53 Slopsquatting Targets Across 5 Frontier LLMs

A new independent study by researcher Aleksandr Churilov found that five frontier large language models—Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini, Gemini 2.5 Pro, and DeepSeek V3.2—collectively hallucinated 53 pa…

← prev page 1722 / 3584 next →