bug report
30 articles about bug report in AI news
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.
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.
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.
How to Prevent Claude Code from Deleting Production Data: The Critical --dry-run Flag
A critical bug report shows Claude Code can delete production databases. Use `--dry-run` and explicit path exclusions in CLAUDE.md immediately.
How to Get Your Claude Code Issues Noticed (When 2,500+ Come In Weekly)
With 49-71% of issues auto-closed, learn the data-backed strategies to make your bug reports stand out and get developer attention.
Claude Quietly Removes Full Thinking Traces, Users Report
Claude may have removed full thinking traces per user reports. Loss for interpretability and debugging. Anthropic has not confirmed.
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.
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.
Vibe Coding to Agentic Coding: A Field Report from Taiwan
TitanSoft's field report argues AI coding shifts from vibe to agentic coding, requiring engineers to design feedback loops. No metrics disclosed.
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.
Aikido Security: AI code tools introduce 23% more bugs per PR on average
AI code assistants increase bug density by 23% per PR; vibe coding yields 3.4x more security warnings. Aikido analyzed 150k repos.
Anthropic Opus 4.8 Cuts Bug-Finding Cost by 5x, SemiAnalysis Finds
Anthropic's Opus 4.8 + ultracode mode cuts severe bug-finding cost to ~1/5, per preliminary SemiAnalysis experiments with wide error bars.
Claude Code Enforces Programmatic API Tiers, 10x Cost Hikes Reported
Anthropic enforces programmatic usage restrictions on Claude Code, with users reporting 10x cost hikes to $1,000/month. The move squeezes power users toward API pricing.
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.
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.
Opus 4.7 AI Hallucinates with High Conviction, Developer Reports
A developer reported that Anthropic's Opus 4.7 model repeatedly hallucinated about a test result, insisting the score was unchanged despite evidence. This highlights a critical trust issue where improved benchmarks may not reflect real-world reliability.
Anthropic Reportedly Deploys AI Model for Zero-Day Vulnerability Discovery
Anthropic has reportedly deployed a frontier AI model for discovering zero-day software vulnerabilities. The model is claimed to have found flaws in code audited by humans for decades.
Cisco's Memory Poisoning Report: Why Claude Code Users Must Audit Their CLAUDE.md Now
A new security report reveals that instructions placed in your CLAUDE.md file can be weaponized to persistently compromise Claude Code's behavior across sessions, demanding immediate file audits.
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.
Google's 'Agent Smith' AI Tool Reportedly in Internal Development, Joining OpenAI 'Spud' and Claude 'Mythos'
A leak suggests Google is developing an internal AI tool codenamed 'Agent Smith,' reportedly popular with employees. It's positioned alongside upcoming releases from OpenAI and Anthropic, signaling a new phase of internal productivity tooling.
Debug Your Browser with Claude Code: The Chrome DevTools MCP Server is a Frontend Game-Changer
Google's official Chrome DevTools MCP server gives Claude Code deep browser debugging, performance profiling, and Lighthouse audits—connect it to your live browser session today.
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.
Claude Code Artifacts: How to Turn Sessions into Shareable Reports (Beta Guide)
Claude Code Artifacts let you publish session context—diffs, logs, decisions—as a hosted page. Prompt with the reader and purpose. Share the URL. No syntax needed.
Claude Code Max Users Report 3–4x Faster Limit Exhaustion
Max plan users see 3–4x faster limit exhaustion. Audit token-heavy tasks, use /compact and CLAUDE.md rules to reduce waste per session.
Feature Freshness: The Production Bug That Makes Good Recommenders Look Bad
Jie Li's article reveals that stale features—outdated user signals—can degrade recommender performance by 20-30% in offline metrics, often misdiagnosed as model problems. The piece urges teams to prioritize feature freshness monitoring alongside model tuning.
Blackwell NVLink Breaks Confidential Compute, 61% Regression Reported
NVIDIA Blackwell confidential computing disables NVLink multicast, causing 61% regression on SGLang Qwen3.5 397B. Hopper had unencrypted NVLink, compounding the issue.
GPT-5.5 Generates Complex SVG in Single Prompt, User Reports
A developer shared that OpenAI's GPT-5.5 produced a sophisticated SVG image from a single prompt. This suggests improvements in the model's ability to generate precise, structured visual code.
Google's Auto-Diagnose AI Hits 90% Accuracy Debugging Test Failures
Google researchers built Auto-Diagnose, an LLM tool that analyzes failure logs to suggest root causes. It achieved 90.14% accuracy in evaluation and was used on over 52,000 distinct failing tests after company-wide deployment.
Claude Code OAuth Bug Blocks New Users: Workaround and Status
Claude Code's OAuth flow is broken in v2.1.107, preventing new auth. Use `claude code auth --manual` to get a token and paste it directly.
AMD AI Director Reports Claude Code Quality Decline, Cites 234k Tool Calls
An AMD AI executive presented data from over 6,800 sessions showing Claude Code's performance has declined since early March, with rising instances of shallow reasoning and incomplete tasks. This raises significant trust issues for engineers using the model in complex development workflows.