RE: mastodon.social/@simple_sabotage/1162332...

Oh, that‘s exactly how AI-bros are trying to sabotage us:

„Never pass on your skill and experience to a new or less skillful worker“

#deskilling #LLM #AI #sabotage #education #codegeneration

CONCUR: Benchmarking LLMs for Concurrent Code Generation Leveraging Large Language Models (LLMs) for code generation has increasingly emerged as a common practice in the domain of software engineering. Relevant benchmarks have been established to evaluat…

CONCUR: Benchmarking LLMs for Concurrent Code Generation

#CodeGeneration #LLM #Package

hgpu.org?p=30644

StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning Modern machine learning (ML) workloads increasingly rely on GPUs, yet achieving high end-to-end performance remains challenging due to dependencies on both GPU kernel efficiency and host-side setti…

StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning

#CUDA #CodeGeneration #LLM

hgpu.org?p=30629

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundame…

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models

#CodeGeneration #LLM #Package

hgpu.org?p=30620

CL4SE: A Context Learning Benchmark For Software Engineering Tasks Context engineering has emerged as a pivotal paradigm for unlocking the potential of Large Language Models (LLMs) in Software Engineering (SE) tasks, enabling performance gains at test time without…

CL4SE: A Context Learning Benchmark For Software Engineering Tasks

#CodeGeneration #LLM #Package

hgpu.org?p=30619

From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation Large Language Models (LLM) show strong abilities in code generation, but their skill in creating efficient parallel programs is less studied. This paper explores how LLMs generate task-based paral…

From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation

#OpenMP #LLM #CodeGeneration

hgpu.org?p=30618

This article on #InfoQ presents a least-privilege AI Agent Gateway that controls how agents access infrastructure.

Every request is:
✅ Validated
✅ Authorized
✅ Executed in isolated, short-lived environments

Read now for more insights 👉 bit.ly/40ys1Dm

#AI #AIagents #MCP #CodeGeneration

Insightful post by @simonwillison.net that aligns with my own experience guiding my engineering team over the last year of AI code-gen adoption - "Good code still has a cost." #ai #codegeneration #agenticai simonwillison.net/guides/agent...

🤖 Los agentes de código son tan buenos como las señales que les das

La calidad del código generado por IA depende de la información que reciba.

https://thenewstack.io/coding-agents-feedback-signals/

#AI #CodeGeneration #SoftwareDevelopment #RoxsRoss

Nice article, but the all-lowercase titling is so jarring:

“Six Thoughts On Generating C”, Andy Wingo (wingolog.org/archives/202...).

Via HN: news.ycombinator.com/item?id=4694...

On Lobsters: lobste.rs/s/j8jnqq/six...

#Programming #C #PLDI #Compilers #CodeGeneration #ProgramSynthesis

Improving Code Generation via Small Language Model-as-a-judge Large language models (LLMs) have shown remarkable capabilities in automated code generation. While effective for mainstream languages, they may underperform on less common or domain-specific langu…

Improving Code Generation via Small Language Model-as-a-judge

#CodeGeneration #LLM

hgpu.org?p=30571

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels Diffusion large language models (dLLMs) have emerged as a compelling alternative to autoregressive (AR) LLMs, owing to their capacity for parallel token generation. This paradigm is particularly we…

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

#CUDA #LLM #CodeGeneration #Package

hgpu.org?p=30569

Improving HPC Code Generation Capability of LLMs via Online Reinforcement Learning with Real-Machine Benchmark Rewards Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempts to train LLMs u…

Improving HPC Code Generation Capability of LLMs via Online Reinforcement Learning with Real-Machine Benchmark Rewards

#CUDA #OpenMP #HPC #CodeGeneration #LLM

hgpu.org?p=30568

O'Reilly: Coding With GPT

O'Reilly: Coding With GPT

#Ai #Chatgpt #Codegeneration #Oreilly #Techbooks

programmerhumor.io/ai-memes/oreilly-coding-...

Spot on.
But remember: in 1900, people "hand-crafted" carriage rides.
In 13 years, NYC swapped hay for horsepower..

Foundations are built to be scaled. We're not losing the craft; we're finally getting the engine we deserve.

#CodeGeneration #Ai #Automation

Flutter Build Systems and Dependency Management: Technical Interview Guide Essential questions and detailed answers covering pubspec.yaml, build modes, flavors, and dependency resolution that experienced Flutter…

I just published Flutter Build Systems and Dependency Management: Technical Interview Guide medium.com/p/flutter-bu...
#Flutter #FlutterDevelopment #FlutterInterview #BuildSystems #DependencyManagement #Pubspec #GradleBuild #FlutterFlavors #CodeGeneration #BuildRunner #MobileDevelopment

Hi #java bubble, which lib do you use and can recommend for #codegeneration ? I've been using square/javapoet and now the fork from #palantir - which feels pretty wrong. I would not like string concatenation because it turns into a maintenance nightmare.
#fedihelp #boostplease

🤖 Cómo maximizar las capacidades agentivas de GitHub Copilot

Guía de un ingeniero senior para arquitecturar y extender sus aplicaciones.

github.blog/ai-and-ml/github-copilot...

#GitHubCopilot #AIEngineering #CodeGeneration #RoxsRoss

The AI Enthusiasm Gap

The AI Enthusiasm Gap

#Ai #Juniordev #Seniordev #Chatgpt #Codegeneration

programmerhumor.io/ai-memes/the-ai-enthusia...

GitHub Copilot CLI Gains Specialized Agents, Parallel Execution, and Smarter Context Management - WinBuzzer GitHub has released an update to Copilot CLI that introduces four specialized agents that can run in parallel, auto-compaction at 95% token limit, and persistent memory for Pro users.

winbuzzer.com/2026/01/16/g...

GitHub Copilot CLI Gains Specialized Agents, Parallel Execution, and Smarter Context Management

#AI #GitHub #GitHubCopilot #AICoding #AICOding #Developers #AIAgents #DeveloperTools #CodeGeneration #AgenticAI #Microsoft #Software #Coding

DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real…

DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation

#CodeGeneration #LLM

hgpu.org?p=30501

AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis Modern AI models demand high-performance computation kernels. The growing complexity of LLMs, multimodal architectures, and recommendation systems, combined with techniques like sparsity and quanti…

AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis

#Triton #CUDA #CodeGeneration #DSL #LLM

hgpu.org?p=30499

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation Parallel programming is central to HPC and AI, but producing code that is correct and fast remains challenging, especially for OpenMP GPU offload, where data movement and tuning dominate. Autonomou…

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

#CUDA #OpenMP #CodeGeneration #LLM #Package

hgpu.org?p=30498

AI-generated code contains more bugs and errors than human output AI-generated code produces 1.7x more issues than human code

Are you worried about the quality of #AI generated code? A new study showed that AI generated code had 1.7X more issues, including 1.4X more critical issues.

www.techradar.com/pro/security...

#LLM #codegeneration #AIHype

The Power of Domain-Driven Design for Code Generation: Why Domain Model Meta Data Driven Templates Beats Your Vibe Coding Prompts In the rapidly evolving landscape of software development automation, vibe coding has become the new hot topic on how to accelerate software engineering. After building an LLM from scratch as well as ...

Code Generation :
Why use templating rather than generative AI?
www.linkedin.com/pulse/power-...

#opensource #codegeneration #codegenerator #modeldriven #softwaredevelopment #softwareengineering #code
#developer #code #programmingtools #genAI #templating

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks l…

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

#CUDA #CodeGeneration #LLM

hgpu.org?p=30467

Claude Code stood out for generating code that matches a developer's style, significantly boosting productivity & maintainability. This unique capability sparked comparisons with tools like Cursor, showcasing its impact on coding workflows. #CodeGeneration 2/5

CodeSOTA - ML Benchmarks & State of the Art Tracking #machinelearning #benchmark #codesota #ocr #speechrecognition #computervision #codegeneration

Git is integrated into Telosys-CLI 4.3.0
Telosys provides a set of Git commands for easily initializing, cloning, and publishing models and bundles to a remote Git server. For more details see doc.telosys.org/git-with-tel...
#opensource #codegeneration #git #softwareengineering #developer #cli

The End of Debugging Software Now Writes, Runs, and Repairs Itself—Our Job Is Shifting from Control to Description.

#CodeGeneration is not just another abstraction layer; it’s a new “atom” for how we think about #software. Once that shift takes hold, we’ll start leveling up—not because we know less but because we’ll be working with more powerful primitives. New #Radar article by Tim O'Brien: bit.ly/44nIVqS