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

Code

Full-text search across 67657 articles. Combine with topic and date filters; results sorted by relevance.

results 67657 page 872/3383 follow RSS for this search
00:00
2026-07-26
zaksa.zip
artificial-intelligence

The new golden age of software development has arrived

Software development has entered a new golden age where AI enables individuals and small teams to build ambitious projects, migrate frameworks in days, and escape vendor lock-in, according to a developer's firsthand acco…

00:53
2026-07-25
dev.to
artificial-intelligence

Weekend #2: Scafolding the 3-Way LLM Orchestration

A developer built a 3-way orchestration system between ChatGPT, Claude, and a local LLM to maintain coding momentum despite token limits. The system, called agent-orchestra, uses Git worktrees to run multiple agents in p…

18:30
2026-07-23
notes.designarena.ai
artificial-intelligence

Kimi K3’s Design Secret may be in its Thinking Traces

Moonshot AI's Kimi K3 open-weight model ranks 1st on Frontend Arena with an Elo of 1392, using over 12x more reasoning tokens than Claude Opus 4.8 and double that of Kimi K2.6. Its performance stems from a unique chain-o…

18:21
2026-07-23
discuss.huggingface.co
artificial-intelligence

What should i change to optimize local hosted AI

A community analysis of local AI coding agent performance identifies several optimization settings for Ubuntu users running llama.cpp/SYCL with dual Intel Arc Pro B70 GPUs and the Qwen3.6-27B model. Key recommendations i…

14:37
2026-07-23
letsdatascience.com
artificial-intelligence

Fleet Tells Lets Data Science Why 7 in 10 Companies Aren't Ready for AI

Fleet Device Management's Road to AI in IT report, based on a survey of over 500 enterprise IT leaders, found that 46.5% rank AI automation as their top investment priority but only 29.6% prioritize infrastructure as cod…

05:10
2026-07-23
runtimewire.com
large-language-models

Head to head: Google: Gemini 3.6 Flash vs gpt-oss-120b

Google's Gemini 3.6 Flash defeated gpt-oss-120b 108.8 to 102.8 in a 12-task head-to-head benchmark, winning 5 tasks to 3 with 4 ties, according to scores from judge gpt-5.4. The win was driven by consistency in code gene…

00:00
2026-07-23
islo.dev
ai-agents

How Obert built a software factory it can trust on Islo

Obert, a provider of go-to-market infrastructure, has built a software factory on Islo that lets its founder, Matan Kleyman, delegate development tasks to AI agents, effectively extending engineering capacity beyond his …

22:31
2026-07-22
ivanmisic.net
artificial-intelligence

Most of My AI Pipeline Isn't AI

A developer's AI pipeline for processing email into notes uses plain Python for most of its code, reserving a language model for only the fuzzy judgment tasks. The pipeline splits work into settled tasks, handled by dete…

14:10
2026-07-22
newsletter.kentbeck.com
ai-agents

How Do You Know That?

Beth Andres-Beck, a software engineer and congressional candidate in Massachusetts' 6th district, argues that the real superpower of engineers is understanding why people do what they do, and that meta-intelligence—learn…

22:04
2026-07-21
github.com
artificial-intelligence

Lower token usage through representation engineering

A new technique called Prompt+Steer, which combines prompting with activation steering, reduces output tokens by an additional ~13% beyond prompting alone on the CodeXGLUE code-to-text task, according to researchers test…

17:17
2026-07-21
poolside.ai
artificial-intelligence

Laguna S 2.1

Poolside released Laguna S 2.1, a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token and a 1M token context window, achieving 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE v1.1 in thi…

15:00
2026-07-21
snowflake.com
artificial-intelligence

The New Partner Playbook: Building in the Age of Snowflake Cortex AI

Snowflake partners must evolve into software-service hybrids as AI tools like Cortex AI enable customers to build prototypes in days, shifting value from time-and-materials to outcome-based delivery. Amy Kodl of Snowflak…

08:40
2026-07-21
dev.to
artificial-intelligence

Stop Letting AI Write Security Bugs: Introducing "hallint"

A developer built hallint, a free open-source static analysis tool specifically tuned to catch security bugs generated by AI coding assistants like Copilot and ChatGPT. The tool scans JavaScript, TypeScript, and Python c…

← prev page 872 / 3383 next →