Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…

bug fix

30 articles about bug fix in AI news

GPT-5.5 Pro Sustains 2-Hour Bug Fixing Sessions

A user reports GPT-5.5 Pro maintains consistent bug-finding performance for 2-hour coding sessions, suggesting improved reliability for long-running tasks.

85% relevant

Claude Code vs. Codex: Real-World Devs Reveal When Each Tool Wins

Claude Code shines at design and greenfield work; pair with Codex for bug fixes. Use CLAUDE.md for guidance.

90% relevant

PaperDebugger Open-Sourced: NUS Tool Auto-Fixes Academic Writing

NUS open-sourced PaperDebugger, an in-editor tool that auto-fixes academic writing clarity and structure. It runs locally via Ollama and catches 40% more issues than Grammarly.

78% relevant

Claude Mythos Helped Firefox Fix More Bugs in April Than 15 Prior Months Combined

Firefox fixed more security bugs in April 2026 than 15 prior months combined, using Anthropic's Claude Mythos Preview model for triage and patching.

86% relevant

Anthropic's Auto-Fix Feature Aims to Revolutionize AI Debugging for Developers

Anthropic has unveiled a research preview feature called Auto-Fix for Claude, designed to automatically correct errors in AI-generated code. This development addresses a persistent pain point for developers working with large language models.

85% relevant

Fix 80% of A11y Bugs Automatically

Install axe-core MCP in Claude Code to auto-detect and patch 80% of WCAG violations, replicating Evinced's agentic a11y workflow.

86% relevant

Claude Code v2.1.86 Fixes /compact Failures, Adds Context Usage Tracking

Latest update fixes critical /compact bug, adds getContextUsage() for token monitoring, and improves Edit reliability with seed_read_state.

95% relevant

Claude Code v2.1.90: /powerup Tutorials, Performance Gains, and Critical Auto Mode Fix

Claude Code v2.1.90 adds interactive tutorials, improves performance for MCP and long sessions, and fixes a critical Auto Mode bug that ignored user boundaries.

95% relevant

7 CLAUDE.md Mistakes That Were Silently Taxing My Sessions (And the Exact Fixes)

Fix your CLAUDE.md workflow: move hard rules to PreToolUse hooks, target reads with grep, and delegate exploration to subagents to reclaim context. First sentence: The fix is moving hard rules to PreToolUse hooks and CLAUDE.md for preferences.

100% relevant

How to Wire LangGraph to MCP: Fix the Broken Connection in 5 Minutes

Connect LangGraph to MCP using MCPClient: call send_request() in your handler, and add retries. This fixes broken agent responses and keeps conversation flows resilient.

82% relevant

Claude Code Subagents Not Being Used? Fix Your description Field First

Fix subagent routing by making `description` a trigger condition, not a title. Use `/doctor` for name collisions and validate `tools` entries. This turns your custom agents into reliable specialists.

100% relevant

Stop Rewriting CLAUDE.md: Use /context and InstructionsLoaded to Debug Why

Use /context and the InstructionsLoaded hook to verify CLAUDE.md files actually load. Fix lazy-loading issues (nested files, @imports) before editing rule wording. Only rewrite rules after confirming they're in context.

100% relevant

Cline v4.1.1 Fixes MCP Routing: Server-Name Stability Ends Restart Chaos

Adopt Cline v4.1.1's server-name routing for MCP; it stabilizes tool calls across restarts. Key fix: McpHub no longer uses random UIDs, so your MCP servers stay connected even after config edits.

75% relevant

Fix MCP Server .env Loading: Stop Depending on cwd with __file__-Relative Paths

Learn why MCP servers must use __file__-relative .env paths. Claude Desktop's config lacks cwd, so relative paths break. Fix: `os.path.join(os.path.dirname(os.path.abspath(__file__)), '.env')`.

82% relevant

Integration Testing Your MCP Server: The Pattern That Caught 3 Hidden Bugs

Integration test your MCP server by spinning it up with STDIO and sending real tools/call requests. This catches startup races, JSON-RPC framing errors, and state bugs that 90% unit test coverage missed.

79% relevant

Fix Claude Code's Broken Duplicate Issue Labels

Claude Code's GitHub action labels issues as duplicates without linking the original, breaking triage. Check workflow logs or wait for fix in #79523.

70% relevant

Build an Adversarial Verifier Loop in Claude Code: Catch Bugs Before They Land

Stop trusting Claude Code's self-reports. Add a 3-verifier panel that refutes changes with concrete repro cases, catching bugs tests miss. Capped at 3 rounds.

78% relevant

Apple's Safari 247 Ships Official MCP Server: Debug Websites from Claude Code

Apple's Safari 247 MCP server lets Claude Code inspect and debug live web pages. Install it via Homebrew and connect to debug rendering or JavaScript issues.

75% relevant

Compass v1.1.0 Ships Recall Consumption Fix 12 Hours After Launch

Nautilus-Compass v1.1.0 fixes a recall consumption failure where agents saw file titles but didn't read bodies, embedding body text in top-3 hits and adding a drift detector for unconsumed recalls.

100% relevant

CLAUDE.md for Mobile: How One File Fixes Claude Code's CSS Blindspot

A specialized CLAUDE.md file fixes Claude Code's generic CSS by injecting mobile-specific rules, preventing iOS zoom, untappable buttons, and dark mode failures before shipping.

95% relevant

Curl Maintainer Finds 1 CVE, ~20 Bugs via Anthropic's Mythos

Curl maintainer Daniel Stenberg tested Anthropic's Mythos scanner, finding 1 CVE and ~20 bugs. Results validate LLM-based security auditing on real-world code.

98% relevant

Claude Code Regression: How to Diagnose and Fix the Recent Quality Drop

Anthropic's postmortem reveals three regressions in Claude Code: reasoning effort, context retention, and verbosity changes. Here's how to diagnose and fix them.

100% relevant

LLM-as-a-Judge Framework Fixes Math Evaluation Failures

Researchers propose an LLM-as-a-judge framework for evaluating math reasoning that beats rule-based symbolic comparison, fixing failures in Lighteval and SimpleRL. This enables more accurate benchmarking of LLM math abilities.

82% relevant

Alibaba's DCW Fixes SNR-t Bias in Diffusion Models, Boosts FLUX & EDM

Alibaba researchers developed DCW, a wavelet-based method to correct SNR-t misalignment in diffusion models. The fix improves performance for models like FLUX and EDM with minimal computational cost.

85% relevant

Google's 'TestPilot' AI Agent Debugs Integration Tests from Logs

Google introduced TestPilot, an AI agent that diagnoses integration test failures by sifting through logs and suggesting code fixes. It autonomously resolved 15% of real-world Python test failures in an experiment.

85% relevant

How Telemetry Settings Are Silently Costing You Cache Tiers (And How To Fix It)

A confirmed bug links telemetry settings to cache TTL; disabling telemetry defaults you to 5-minute cache, increasing costs. Use environment variables and hooks to mitigate.

90% relevant

Claude Code's Auto-Close Policy: What It Means for Your Bug Reports

Claude Code's GitHub repo automatically closes inactive issues after 14 days—understand this policy to ensure your bug reports get attention.

100% relevant

Anthropic's Claude AI Identifies Security Vulnerabilities, Earns $3.7M in Bug Bounties

Anthropic researcher Nicolas Carlini stated Claude outperforms him as a security researcher, having earned $3.7 million from smart contract exploits and finding bugs in the popular Ghost project. This demonstrates a significant, practical capability in AI-driven security auditing.

87% relevant

Linux Kernel Maintainer Linus Torvalds Reports AI-Generated Bug Reports Now Contain 'Actual Bugs' and Working Patches

Linus Torvalds, the lead maintainer of the Linux kernel, has stated that AI-generated bug reports are no longer 'slop' and now frequently identify real bugs with working patches. This marks a significant shift in the practical utility of AI for large-scale, complex software maintenance.

85% relevant

This Notion MCP Bug Tracker Automates Error Logging—Here's How to Use It

A new MCP server automatically logs and categorizes errors to Notion, turning raw console output into structured bug reports.

74% relevant