34 stories, newest first · one card per story
The author prompts Claude to explore building a custom SQLite function that parses strings like '-$1,234.56' into numbers, comparing C and Rust implementations on performance and code size.
Author switches from Claude Code to Pi citing IDE integration limits, bloated prompts and unstable updates.
Cursor's Composer 2.5 agent over-deletes functions, forgets parameters and mishandles refactoring while introducing new errors during coding tasks.
Glow Labs research found AI agents installing deprecated MCP servers in 98% of sessions, with four high-severity vulnerabilities including RCE, downloaded over 17.3 million times, no patches or exploitation seen.
Pull requests adding AI coding assistant configuration files can distribute executable hooks to developer machines without changing app source code.
Employees say AI use may decide who keeps a job, and leadership did not dispute the account.
Walcutt says his research found 44% of AI-generated coding tasks introduced a known vulnerability.
Stateless reviewer sessions must restate the design and hunt gaps before a go/no-go on files and signatures.
Kernel maintainers are dropping the Assisted-by tag, so submitters no longer must disclose AI use.
Some linked-provider users report overnight charges up to $1,700 and Google Cloud project suspensions.
Replit’s CEO says OpenAI’s ChatGPT is now the default for Replit Agent over Anthropic.
A Faros study and tooling survey say AI coding raises bugs and incidents unless automated verification keeps pace.
The Claude Code team uses continuous Claude review so humans focus on higher-level code risks.
Replit's CEO says the company dropped Anthropic for OpenAI over cost and performance.
Linus Torvalds says Claude Code drafted supervised Linux patches that speed cached small reads.
Symantec says the Aoki infostealer now steals API keys and sessions from AI coding assistants.
JetBrains finds most DevOps teams run CI/CD, while AI-generated changes slow code reviews.
Epic Games released a preview launcher rewritten with AI that it says starts faster than Steam.
Anthropic built custom source control after daily merges jumped from 2,500 to over 30,000.
A study finds AI coding agents speed coding but raise pull-request review time 49% and change requests.
An anonymous engineer says Claude Code reduced his team to long days of approving AI-generated code.
An engineer says Claude Opus 4.5 in Claude Code ended his 18-year habit of writing code by hand.
UpGuard found over 16,000 misconfigured Supabase databases exposing PII, passwords, tokens, and some payment data.
Anthropic offers Pro and Max subscribers up to $250 in free Claude Code credits for cloud sessions only.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views