Deleting 19k Lines of Dead Compiler Code Without Trusting the LLM
TheCloudlet demonstrates a method to safely delete 19,000 lines of dead compiler code by using AI to identify candidates and then relying on human verification to avoid errors.
#code
Code
16 stories tagged Code
TruVerif Launches Panel of Four AI Models That Debate the Riskiest Code in Your AI Agent
TruVerif introduced a panel of four frontier AI models that collaboratively debate and identify the riskiest aspects of AI agent code. The panel review aims to improve AI safety by surfacing technical vulnerabilities, ethical concerns, and potential misuse through structured multi-model debate.
Multi-Agent Code Judge Declines to Guess When Evidence Is Insufficient
A new ArXiv paper introduces a multi-agent verification system that judges code correctness by decomposing judgments into checkable claims and verifying each against independent evidence. Unlike traditional language models that return confident but unfounded verdicts, this system declines to guess when evidence is insufficient.
Anthropic reveals how Claude's new watermarks will detect AI-generated text and code
Anthropic has announced new watermarking technology for Claude that embeds imperceptible patterns in AI-generated text. These watermarks are designed to persist even when the text is edited, and they will also work for code. The feature is set to roll out in the coming weeks.
TokenScope: New Tool Helps Explain AI Code Generation Decisions
Researchers developed TokenScope, a tool that reveals how AI models make decisions when writing code. It provides real-time insights into the AI's thought process, helping developers understand and trust AI-generated code.
New AI Technique Improves Visual Output from Code-Generating Models
Researchers developed a method to enhance visual artifacts created by code-generating AI models. This technique helps fix common issues like overlapping elements and low contrast in generated charts and web pages.
AI Program Editing Gets Stuck in Repetitive Loops, Study Finds
When AI models edit code repeatedly, they tend to recycle the same solutions rather than exploring new ones. This could limit how creative AI tools can be when helping programmers. Researchers found that in 87% of mutation chains, over 93% of AI-generated code mutations revisited familiar structural forms.
AI now finds software vulnerabilities faster than they get patched
AI tools are now identifying software flaws faster than developers can fix them. This shift is changing how companies approach cybersecurity. These tools can scan code for weaknesses in seconds, but fixing them still requires human time and effort.
How Ramp Engineers Use AI to Speed Up Code Reviews
Ramp engineers are using OpenAI's Codex with GPT-5.5 to get faster code reviews. This AI tool helps them identify issues and suggest improvements in minutes, not hours. It's like having a super-smart assistant that never gets tired.
Revos: New Tool Checks AI-Generated Code for Architectural Flaws
Revos is an open-source tool that scans AI-generated code for architectural issues. It helps developers catch potential problems early in the coding process.
Machine-Generated Code Deserves Machine-Checked Proofs
As AI-generated code becomes more prevalent, formal verification is crucial to ensure reliability and security. This shift requires new tools and methodologies to validate machine-written software.
VibeDrift: Tracking Drift in AI-Generated Codebases
VibeDrift is a new tool designed to measure drift in AI-generated codebases. It helps developers monitor changes and maintain consistency in code produced by AI models.
Formal: Lean 4 for Verifying AI-Generated Code
A new tool called Formal uses Lean 4 to verify AI-generated code, ensuring correctness and reliability. This could revolutionize AI-assisted programming by adding a layer of mathematical proof to code outputs.
Cognitive Debt: The Hidden Cost of AI-Generated Code
AI-generated code introduces 'cognitive debt,' making systems harder to understand and maintain. This new challenge could outweigh traditional technical debt.
Claude Code Creator Reveals Workflow, Sparks Developer Revolution
Boris Cherny, creator of Claude Code, shared his terminal setup on X, sparking a viral discussion. Developers worldwide are adopting his methods, calling it a watershed moment for software development.
Waymo Rule for AI Code
The Waymo Rule proposes guidelines for AI-generated code. It aims to ensure accountability and transparency in AI development.