#CodeGeneration

Fazen Capital

@fazencapital.bsky.social

2 days ago

Vibe Coding Shifts Bottleneck to Trust in Enterprise IT Vibe coding accelerates code generation (ChatGPT Nov 30, 2022; GPT-4 Mar 14, 2023) but Fortune (Apr 2, 2026) finds verification has become the primary bottleneck for large enterprises.

Vibe Coding Shifts Bottleneck to Trust in Enterprise IT: Vibe coding accelerates code generation (ChatGPT Nov 30, 2022; GPT-4 Mar 14, 2023) but Fortune (Apr 2, 2026) finds verification has become the primary… 👈 Read full analysis #VibeCoding #EnterpriseIT #AI #CodeGeneration #DeveloperWorkflows

@emergingtechnews.bsky.social

4 days ago

Google Launches Open Model Family Gemma 4 Google Launches Open Model Family Gemma 4

#Google launched #Gemma4, a new family of open-weight #AI models. Designed to deliver major advancements in #reasoning, #CodeGeneration & complex #LogicTasks; built using the same research & tech as Gemini 3 but marks a significant leap forward in #capabilities. aibusiness.com/generative-a...

Pixels and Pulse - Blog

@pixelsandpulse.bsky.social

4 days ago

Apple's "simple" AI trick for code generation sounds great, but is it a breakthrough or just cleaning up a messy dataset? We dig into the real story.

thepixelspulse.com/posts/apple-self-distill...

#apple #codegeneration #selfdistillation

Winbuzzer

@winbuzzer.com

4 days ago

AI Coding: OpenAI Switches Codex to Pay-as-You-Go, Cuts Seat Cost to $20 OpenAI has replaced fixed per-seat Codex licenses with pay-as-you-go token billing for ChatGPT Business and Enterprise, cutting the base price to $20.

winbuzzer.com/2026/04/04/o...

OpenAI Switches Codex to Pay-as-You-Go, Cuts Seat Cost to $20

#OpenAI #Codex #AIAgents #ChatGPT #ChatGPTBusiness #EnterpriseAI #Developers #DeveloperTools #SoftwareDevelopment #CodeGeneration

Kubernetes

@kubernetes.activitypub.awakari.com.ap.brid.gy

1 week ago

一天重写 JSONata，我用 400 美元干掉了公司 50 万美元的 K8s 集群 本文永久链接 – tonybai.com/2026/04/01/rewrote-jsona... 大家好，我是Tony Bai...

#技术志 #AIDriven #AI驱动 #ArtificialIntelligence #AutomationTools #CodeGeneration #CostOptimization #CrossLanguageRPC #Go #Golang #GoLanguage

Origin | Interest | Match

Kubernetes

@kubernetes.activitypub.awakari.com.ap.brid.gy

1 week ago

一天重写 JSONata，我用 400 美元干掉了公司 50 万美元的 K8s 集群 本文永久链接 – tonybai.com/2026/04/01/rewrote-jsona... 大家好，我是Tony Bai...

#技术志 #AIDriven #AI驱动 #ArtificialIntelligence #AutomationTools #CodeGeneration #CostOptimization #CrossLanguageRPC #Go #Golang #GoLanguage

Origin | Interest | Match

AI & ML News

@ai-news.at.thenote.app

1 week ago

Beyond Code Generation: AI for the Full Data Science Workflow

Using Codex and MCP to connect Google Drive, GitHub, BigQuery, and analysis in one real workflow

Telegram AI Digest
#ai #codegeneration #datascience

AI и ML Новости

@ai-ru.at.thenote.app

1 week ago

За пределами генерации кода: ИИ для полного рабочего процесса Data Science

Используя Codex и MCP для подключения Google Drive, GitHub, BigQuery и анализа в одном реальном рабочем процессе

Telegram ИИ Дайджест
#ai #codegeneration #datascience

Ricardo Peres

@rjperes.bsky.social

1 week ago

Generating Structured Code Using Azure, OpenAI and .NET Generating Structured Code Using OpenAI and .NET

Generating Structured Code Using Azure, OpenAI and .NET developmentwithadot.blogspot.com/2026/03/gene... #dotnet #ai #openai #llm #codegeneration

Winbuzzer

@winbuzzer.com

1 week ago

90% of Claude Code Output Lands in Low-Star GitHub Repos Anthropic's Claude Code has surpassed 20 million GitHub commits, but 90% of output has landed in repos with fewer than two stars, suggesting hobbyist use.

winbuzzer.com/2026/03/26/c...

90% of Claude Code Output Lands in Low-Star GitHub Repos

#AI #Anthropic #GitHub #Claude #ClaudeCode #AICoding #GenAI #SoftwareDevelopment #CodeGeneration #VibeCoding #Developers

Aljoscha Rittner (beandev)

@beandev.social.tchncs.de.ap.brid.gy

2 weeks ago

Dieses Argument, da ja Menschen auch schlechten Sourcecode schreiben, könne man das bei AI generierten Code auch tolerieren, bringt mich echt an meine Grenzen.

Man gibt alle Qualitätskriterien auf, die für menschliche Devs gegolten haben. Warum gibt man sie auf? Weil ein Dev-Team mit PR 4-eyes […]

LLMs

@llms.activitypub.awakari.com.ap.brid.gy

2 weeks ago

告别古法编程黄金时代：AI 时代不会再有新编程语言诞生的土壤 本文永久链接 – tonybai.com/2026/03/24/no-soil-for-n... 大家好...

#技术志 #AgenticCoding #AIProgramming #AI编程 #AndrejKarpathy #ArtificialIntelligence #C #ClaudeCode #CodeGeneration #CorpusHegemony #Cpp

Origin | Interest | Match

LLMs

@llms.activitypub.awakari.com.ap.brid.gy

2 weeks ago

OpenAI 创始人盛赞 Rust，却遭开发者反驳：Go 才是大模型眼里的“香饽饽”！ 本文永久链接 – tonybai.com/2026/03/23/go-is-the-bes...

#技术志 #Agent #boring #CodeGeneration #ConcurrencyModel #ConsistentStyle #Context #Go #gofmt #Golang #GoLanguage

Origin | Interest | Match

HGPU group

@hgpu.bsky.social

2 weeks ago

MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices? Large language models (LLMs) have demonstrated remarkable capabilities in code generation, yet their potential for generating kernels specifically for mobile devices remains largely unexplored. In …

MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?

#CUDA #LLM #CodeGeneration

hgpu.org?p=30695

AI Daily Post

@aidailypost.com

2 weeks ago

Discover how Abacus AI’s all‑in‑one platform could replace 10+ dev tools—think code generation, agent orchestration, and DeepAgent‑powered workflows. Is it the next vibe in software development? Dive in! #AbacusAI #AIWorkflows #CodeGeneration

🔗 aidailypost.com/news/abacus-...

Tang Vu

@tangvu.bsky.social

2 weeks ago

Key shift: researchers are moving beyond "can ChatGPT code?" toward security, automated testing, and bug repair.

Full study coming soon in a Q1 journal 📄

#LLM #SoftwareEngineering #AI #Research #Bibliometrics #CodeGeneration #MachineLearning

Pixels and Pulse - Blog

@pixelsandpulse.bsky.social

2 weeks ago

Your 'detailed' spec might be sabotaging your distributed system. Learn why natural language fails to prevent critical architectural flaws, even with LLMs generating code.

thepixelspulse.com/posts/detailed-spec-is-c...

#distributedsystems #llms #codegeneration

Thodoris Kouleris

@tkouleris.eu

2 weeks ago

GitHub - drpaneas/revibe: Reverse Vibe Coding Reverse Vibe Coding. Contribute to drpaneas/revibe development by creating an account on GitHub.

Revibe is a Go CLI that reverse-engineers code into a precise Markdown spec, regenerates it via an LLM, and iteratively refines until outputs match exactly.

#ReverseEngineering #LLMTools #CodeGeneration

ProgrammerHumor.io

@programmerhumor-io.bsky.social

3 weeks ago

Slopmax On My Bubble Till I Pop

Slopmax On My Bubble Till I Pop

#Ai #Copilot #Chatgpt #Claude #Codegeneration

programmerhumor.io/ai-memes/slopmax-on-my-b...

glamcode

@glamcode.openbiblio.social.ap.brid.gy

3 weeks ago

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

HGPU group

@hgpu.bsky.social

1 month ago

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

HGPU group

@hgpu.bsky.social

1 month ago

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

HGPU group

@hgpu.bsky.social

1 month ago

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

HGPU group

@hgpu.bsky.social

1 month ago

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

HGPU group

@hgpu.bsky.social

1 month ago

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

InfoQ

@infoq.com

1 month ago

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

Sai Prakash

@sylonzero.bsky.social

1 month ago

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...

roxsross

@roxsross.bsky.social

1 month ago

🤖 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

Ranjit Mathew

@rmathew4bs.bsky.social

1 month ago

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

HGPU group

@hgpu.bsky.social

1 month ago

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