#code-generation

[ follow ]
Software development
fromInfoQ
6 days ago

Qwen Team Releases Qwen3-Coder, a Large Agentic Coding Model with Open Tooling

Qwen3-Coder is a new AI code model family focusing on long-context programming tasks, enhancing execution and decision-making capabilities.
fromInfoWorld
6 days ago

JetBrains working on higher-abstraction programming language

JetBrains is creating a new programming language to enhance AI and code controllability and transparency.
#ai-coding
fromWIRED
1 week ago
Software development

Cursor's New Bugbot Is Designed to Save Vibe Coders From Themselves

fromWIRED
1 week ago
Software development

Cursor's New Bugbot Is Designed to Save Vibe Coders From Themselves

more#ai-coding
Software development
fromZDNET
1 week ago

9 programming tasks you shouldn't hand off to AI - and why

AI cannot replace human programmers completely as many programming tasks require human judgment and contextual understanding.
fromDevOps.com
1 week ago

Harness Extends AI Reach to Include Generating DevOps Pipelines - DevOps.com

Harness AI allows plain language to create corporate-standard pipelines and recommends fixes for errors in minutes.
fromDevOps.com
1 month ago

Secure Code Warrior Defines Security Rules for AI Coding - DevOps.com

Secure Code Warrior's AI Security Rules guide developers in reviewing AI-generated code for security issues.
#ai
fromInfoQ
4 months ago
Artificial intelligence

Google Introduces Gemini 2.5 Pro with Improved Reasoning and Coding Capabilities

Artificial intelligence
fromInfoQ
4 months ago

Google Introduces Gemini 2.5 Pro with Improved Reasoning and Coding Capabilities

Gemini 2.5 Pro enhances AI reasoning and coding capabilities, achieving top scores in multiple benchmarks despite some integration issues.
more#ai
#artificial-intelligence
more#artificial-intelligence
Startup companies
fromFast Company
1 month ago

AI code-gen startup valuations surge as Big Tech circles

Code generation startups are experiencing high valuations despite challenges, indicating a shift in software development aided by AI.
Scala
fromHackernoon
9 months ago

Running Quantized Code Models on a Laptop Without a GPU | HackerNoon

The research utilizes the llama-cpp-python package for efficient quantization of LLMs in a Windows 11 Python environment.
Scala
fromHackernoon
9 months ago

Why Lua Is the Ideal Benchmark for Testing Quantized Code Models | HackerNoon

Lua presents unique challenges for quantized model performance due to its low-resource status and unconventional programming paradigms.
Software development
fromInfoQ
2 months ago

Windsurf Launches SWE-1 Family of Models for Software Engineering

Windsurf's SWE-1 models support diverse software engineering tasks while improving performance and user experience.
#ai-in-software-development
Artificial intelligence
fromIT Pro
2 months ago

'Developers will need to adapt': Microsoft CEO Satya Nadella joins Google's Sundar Pichai in revealing the scale of AI-generated code at the tech giants - and it's a stark warning for software developers

Microsoft's Satya Nadella says AI is responsible for 20-30% of the company's code, indicating a transformative trend in software development.
fromTechCrunch
3 months ago
Artificial intelligence

Microsoft CEO says up to 30% of the company's code was written by AI | TechCrunch

Artificial intelligence
fromIT Pro
2 months ago

'Developers will need to adapt': Microsoft CEO Satya Nadella joins Google's Sundar Pichai in revealing the scale of AI-generated code at the tech giants - and it's a stark warning for software developers

Microsoft's Satya Nadella says AI is responsible for 20-30% of the company's code, indicating a transformative trend in software development.
fromTechCrunch
3 months ago
Artificial intelligence

Microsoft CEO says up to 30% of the company's code was written by AI | TechCrunch

more#ai-in-software-development
fromHackernoon
1 year ago

Unlocking Structured Commonsense Reasoning with Code-LLMs | HackerNoon

COCOGEN leverages code-generation capabilities of large language models for effective structured commonsense generation.
fromHackernoon
1 year ago

Using Code-LLMs for Symbolic and Structured Reasoning | HackerNoon

Existing methods for structured commonsense generation typically flatten the output graphs as strings, which often struggles with the generation of well-formed outputs.
Scala
Artificial intelligence
fromDevOps.com
3 months ago

AI-Generated Code Packages Can Lead to 'Slopsquatting' Threat - DevOps.com

AI hallucinations can lead to incorrect or made-up package recommendations, posing security risks for software developers.
Artificial intelligence
fromTechCrunch
3 months ago

OpenAI pursued Cursor maker before entering into talks to buy Windsurf for $3B | TechCrunch

OpenAI shifts focus from Anysphere to Windsurf for acquisition to capture code generation market quickly.
fromHackernoon
4 months ago

Think-and-Execute: The Experimental Details | HackerNoon

The study uses various large language models (LLMs) for experimental tasks, emphasizing differences in performance and inference times.
fromHackernoon
4 months ago

Our Analysis on Think-and-Execute and Pseudocode | HackerNoon

Task-level pseudocode significantly improves reasoning performance compared to instance-specific logic.
Pre-training on code corpora enhances the understanding of task-level logic.
#vibe-coding
fromTechCrunch
4 months ago
London startup

TurinTech reveals $20M in backing to fix problems in 'vibe coding' | TechCrunch

Vibe coding, facilitated by LLMs, raises concerns about efficiency and security in AI-generated code, prompting the launch of TurinTech's solution, Artemis.
Software development
fromTechzine Global
4 months ago

'Vibe coding' increasingly becoming standard for development

'Vibe coding' democratizes code writing but may compromise traditional software development standards.
While vibe coding resembles rapid code writing, it poses risks like bugs needing human oversight.
London startup
fromTechCrunch
4 months ago

TurinTech reveals $20M in backing to fix problems in 'vibe coding' | TechCrunch

Vibe coding, facilitated by LLMs, raises concerns about efficiency and security in AI-generated code, prompting the launch of TurinTech's solution, Artemis.
Software development
fromTechzine Global
4 months ago

'Vibe coding' increasingly becoming standard for development

'Vibe coding' democratizes code writing but may compromise traditional software development standards.
While vibe coding resembles rapid code writing, it poses risks like bugs needing human oversight.
more#vibe-coding
UX design
fromMedium
4 months ago

Figma to functional: AI-powered iteration with Anima's Playground

Prepare Figma designs for Anima by organizing layers, using frames, and implementing auto-layout to optimize code generation.
Scala
fromhackernoon.com
4 months ago

Tired of Hardcoded Strings? This Kotlin Multiplatform Trick Makes Localization Effortless

Localization in Kotlin Multiplatform projects is inefficient due to static resources requiring app redeployments for text updates.
Existing solutions like Compose Resources and MOKO Resources are limited and fail to accommodate dynamic localization.
Software development
fromInfoWorld
5 months ago

Review: Gemini Code Assist is good at coding

Google's new AI coding assistant, Gemini Code Assist, assists with code writing, testing, and debugging while maintaining user data privacy.
#github-copilot
fromInfoQ
8 months ago
Web design

GitHub and Google Cloud Collaborate to Bring Gemini 1.5 Pro to GitHub Copilot

fromInfoQ
8 months ago
Web design

GitHub and Google Cloud Collaborate to Bring Gemini 1.5 Pro to GitHub Copilot

more#github-copilot
fromHackernoon
1 year ago

Textbooks Are All You Need: Conclusion and References | HackerNoon

High-quality data significantly enhances the performance of language models in code generation tasks, allowing smaller models to outperform larger ones.
[ Load more ]