#Code Generation
40 articles with this tag
Copilot's Smarter Context Handling
GitHub Copilot is optimizing its AI interactions with smarter context handling and dynamic model routing, making coding assistance more efficient and cost-effective.
Copilot CLI Gains Smarts with LSP
GitHub Copilot CLI now uses Language Server Protocol for true code intelligence, replacing brittle text searches with semantic analysis.
Code2LoRA: Repository Context without Overhead
Code2LoRA generates dynamic LoRA adapters for code LLMs, offering repository context without inference overhead and adapting to evolving codebases.
NF-CoT: High-Bandwidth Latent Reasoning
NF-CoT framework enables high-bandwidth latent reasoning using normalizing flows, boosting LLM performance and efficiency while preserving autoregressive strengths.
Visual AI's Next Act: Generating Code, Not Just Pixels
Visual AI is shifting from static image generation to creating editable code artifacts, unlocking new levels of iteration and production integration, especially in 3D.
Claude Code's Latest Updates
Claude Code rolls out Opus 4.8 as default, introduces dynamic workflows, security plugins, and performance enhancements for developers.
Code as the Agent Harness
Code is evolving into the foundational 'harness' for AI agents, enabling more executable, verifiable, and stateful systems across diverse applications.
LLMs Slash Neural Architecture Search Costs
Delta-Code Generation uses LLMs to produce compact architecture refinements, dramatically cutting costs and improving NAS efficiency.
AI Agents Failures & How To Stop Them
Danilo Campagna from Posthog discusses common LLM code generation failures and strategies for improvement, focusing on context, architecture, and human error.
Matt Carey on AI Agents and Cloudflare's API
AI Engineer Matt Carey discusses how APIs are empowering AI agents, moving towards shared services and the future of Cloudflare's MCP.
Sunil Pai on AI Agents & the Future of Software
Cloudflare's Sunil Pai discusses the future of AI agents, moving from tool-calling to code generation for more efficient and powerful interactions.
InCoder-32B: Bridging General and Industrial Code AI
InCoder-32B, a 32B-parameter model, bridges the gap in code LLMs for industrial applications by unifying chip design, embedded systems, and more with a novel 128K context training.
Mistral AI's Leanstral Tackles Trust in Code Generation
Mistral AI introduces Leanstral, an open-source code agent for Lean 4, aiming to bring formal verification to AI-generated code and boost engineering efficiency.
LLMs Fail Esoteric Code Tasks
Frontier LLMs show a dramatic capability gap on a new benchmark using esoteric programming languages, revealing a reliance on memorization over reasoning.
GitHub Copilot Agent Gets Smarter
GitHub Copilot coding agent receives major updates, including model selection, self-review, integrated security scanning, custom agents, and CLI handoff, significantly enhancing its automation and code quality capabilities.
Hybrid Scaling and Peer Review Elevate Software Engineering Agents
The TEX framework uses cross-candidate execution feedback to create collaborative Software engineering agents, achieving state-of-the-art results in test generation.
Your Support Team Should Ship Code, Lisa Orr, Zapier
Beyond Snippets: The Evolving Landscape of AI Code Evaluation
AI Transforms Product Development for Startups
Claude Code Redefines Developer Workflows on Desktop
Codex Max is here: OpenAI’s AI can now code for 24 hours
Inception raises $50M to build diffusion models for code
AI startup Inception raised $50 million to develop diffusion models, a generative AI technique for creating high-quality software code and text.
CoDA Code Generation Shifts AI Paradigm
Poolside reportedly raising up to $1B to advance AI code generation
AI code generation startup Poolside is reportedly raising up to $1 billion from investor Nvidia to build tools that accelerate software development.
CoreStory raises $32M to advance AI legacy code modernization
AI startup CoreStory raised $32 million to help enterprises modernize legacy software with its platform that automatically documents and analyzes old code.
AI Turbocharges Engineers, Creates New Visibility Imperative for Software Teams
Gemini Achieves Gold-Level: AI's Code Breakthrough
GPT-5 Ignites Moderna's Second Computing Revolution
DeepSeek V3.1: The Revolutionary Hybrid AI Model Transforming the Agent Era (2025 Complete Guide)
What is DeepSeek V3.1? The Next Evolution in AI Technology DeepSeek V3.
DeepSeek V3.1: The Revolutionary Hybrid AI Model Transforming the Agent Era (2025 Complete Guide)
What is DeepSeek V3.1? The Next Evolution in AI Technology DeepSeek V3.
The Quest for AI Engineering's Standard Model
ChatGPT-5 Generates, Solves Complex Rubik's Cubes
GPT-5 Redefines AI Utility with Deep Reasoning and Broad Application
Execution is the Moat: Sarah Guo's State of AI Startups
AI's Code: More Artifact, Less Architecture
Redefining Codebase Mastery: A Look at Augment Code's AI Assistant
OpenAI's Unseen Models Redefine AI Frontiers
Lovable Secures $200M Series A, Achieves Unicorn Status
Lovable Secures $100 Million in Reported Funding Round
