code-generation |

When Code Becomes Too Cheap: The Code-Bloat Problem in AI-Generated Software

Rule Engine + LLM Hybrid Architectures for Safer Code Generation

The Architect and the Apprentice: Retaining Control in the Age of Code Generation

From Program to Sketch: Modeling Non-Deterministic Observations in Code Generation

Syntactically Valid Code Editing: A Training Methodology for Neural Program Synthesis

Inverting the Observation Model: How to Generate Code from Any Output

From Images to Programs: A Denoising Diffusion Method for Inverse Graphics

The Assembly Line of Code: AI as the Fordism of Software

A Practical Guide to Prompting Fully Featured Platforms in single prompt

A Look At The Data: Blogs, Forums, And The Rise Of LLM Tools

The Great Transformation: How LLMs Remake Every Programming Activity

Excel vs. Python: How The Target Language Changes Everything For Non-Experts

The AI Gardener: A New Role For Experts In A World Of Automated Code

Making Code Make Sense: The Challenge Of Comprehension In AI-Driven Programming

Beyond The Final Answer: Why Non-Experts Can’t Spot Bad AI Code

Thinking Like A Computer: The Missing Skill For Non-Experts Using AI

Why It’s Harder: The Unique Hurdles For Non-Experts Using AI Coding Tools

Boosting Developer Productivity: The Secret To Taming Repetitive Code

The Uncanny Valley Of Code: Why AI-Generated Code Is So Hard To Debug

Let’s Hear From The Developers: What It’s Really Like To Code With AI

Let’s Talk Usability: Unpacking The User Experience Of AI-Assisted Programming

The Dark Side Of AI: Reliability, Safety, And Security In Code Generation

GitHub Copilot Leads The Charge In Commercial LLM-Assisted Programming

A Quick Guide To LLM Code Generation Technology And Its Limits

Solving Coding Puzzles: The Evolution of Programmer Assistance Tools

Can Anyone Code Now? Exploring AI Help for Non-Programmers

Model Inversion Efficacy & Qualitative Vulnerability Examples from LLMs

The Art of Prompt-Swapping, Temperature Tuning, and Fuzzy Forensics in AI

An Analysis of ChatGPT Instructions, Few-Shot Scaling, and C Code Vulnerability Generation

LLM Details & Finding Security Vulnerabilities in GitHub Copilot with FS-Code

Echoes in the Code: The Lasting Impact and Future Path of AI Vulnerability Benchmarking

Experimenting with ChatGPT’s Vulnerability Volcano and Prompt Party Tricks

Systematic Discovery of LLM Code Vulnerabilities: Few-Shot Prompting for Black-Box Model Inversion

Unveiling the Code Abyss: Inverting LLMs to Expose Vulnerability Vortexes in AI-Generated Programs

Benchmarking LLM Susceptibility to Generating Vulnerable Code via Few-Shot Model Inversion

Automating Kotlin Data Class Testing with KSP

Real-World Code Performance: Multi-Token Finetuning on CodeContests

Unlocking Generative Power: Multi-Token Prediction for Next-Gen LLMs

Podcast: GitHub Next: how their research and prototyping team operates

Self-Speculative Decoding Speeds for Multi-Token LLMs

Common Problems with GitHub Copilot (And How to Solve Them)

How Effective Is GitHub Copilot?

How GitHub and Stack Overflow Data Were Verified for Research Accuracy

Exploring User Needs and Satisfaction with GitHub Copilot

GitHub Copilot can generate types from your GraphQL schema

Mistral Introduces AI Code Generation Model Codestral

AI-Based Code-Completion Tool Tabnine Now Offers Automatic Unit Test Generation

Turn Your Figma Designs into Code with a Single click

Tools that you don’t know you need for development

Are You Going to be Replaced by Code-Generating AI?

Writing a Code Generator in Go