A longtime Claude Code user announced they are retiring the tool as their main coding harness in favor of Pi, citing accumulated frustrations with the product. The author noted that Anthropic added support for AGENTS.md files shortly after the switch decision was made, but said the change came too late to reverse their choice. Specific complaints included incompatibility between CLAUDE.md and AGENTS.md formats and a VSCode IDE integration limitation allowing only one connected session at a time.
caleb.software
· 2026-11-08
Security researchers reportedly identified 1,122 public GitHub files containing exposed passwords and credentials tied to use of Claude Code's 'Don't Ask Again' permission setting. The feature appears to let the AI coding assistant bypass repeated confirmation prompts, which in these cases allowed sensitive secrets to be committed to public repositories. The finding was published via Apiiro, an AI application security firm.
apiiro.com
· 2026-11-07
Researcher Derik Kauffman discovered a hidden list of over 100,000 words and phrases blocked from iOS autocomplete and swipe-typing across major languages, and published it online. The list includes slurs, sexual and drug terms, but also political phrases like 'dictator Trump,' 'sleepy Joe,' and 'covid was a hoax,' plus inconsistencies such as blocking 'bad girl' but not 'bad boy.' Kauffman extracted the list from a hash table buried in iOS using AI coding tools, and another researcher independently verified the findings; Apple told Reuters the keyboard avoids suggesting potentially offensive terms but doesn't stop users from typing them manually.
theverge.com
· 2026-11-06
Anthropic analyzed 207,000 Claude and Claude Code research sessions using privacy-preserving methods to map how scientists use the AI across fields and tasks. It found heavier relative use in formal sciences like computer science, mathematics and statistics, and lighter use in health and lab-based physical sciences, with data analysis and writing dominating usage—accounting for roughly a third of Claude sessions and nearly half of Claude Code sessions.
anthropic.com
· 2026-11-06
Using Codex and Claude Code to run simulated construction trials, an experiment determined the tallest stable Jenga tower achievable at floor tilts ranging from 0.1° to 25°. On a perfectly flat surface, all 54 blocks stood on end would reach 4.05 meters but collapse at just a 0.21° tilt; the AI-driven search instead found optimal heights for each tilt angle, ranging from 331.5 cm at 0.1° down to 19 cm at 25°.
johnjwang.com
· 2026-11-05
Developer Andrew Boldi released tmux-restore, an open-source tool that automatically saves tmux sessions, windows, panes, working directories and scrollback every minute and again at shutdown. It restores them on restart, and panes running coding agents like Claude Code, Codex, Gemini CLI, opencode or pi resume their exact prior conversations. The tool is installed via a shell script and builds on existing tmux-resurrect and tmux-continuum plugins.
github.com
· 2026-11-03
Anthropic programmer Addy Osmani said Claude Code will now decline prompts asking it to recreate or decompile existing commercial video games. The change alters behavior that previously made the AI coding tool notably capable of reproducing known games' mechanics and assets.
techspot.com
· 2026-11-03
deepsense.ai has published a playbook of ten patterns for structuring repositories and workflows around AI coding agents, developed after its team built HyperCode, a repository intelligence layer, during an OpenAI Codex hackathon. The patterns cover making repos agent-readable through documentation like AGENTS.md, compiling context just-in-time for tasks, and using validation loops to turn recurring agent mistakes into guardrails. The team tested these approaches internally across staff with varying experience using Codex and Claude Code.
deepsense.ai
· 2026-11-03
Revolut has migrated roughly 2,000 engineers to a self-hosted GLM model for coding, running it on 56 Nvidia B200 GPUs, according to David Abitbol, who leads AI operations at the company. Claude Code and Codex, previously the default tools from Anthropic and OpenAI, have been moved to an exception list, with Abitbol citing a blended cost of about 30 cents per million tokens, roughly a tenth of prior spend.
twitter.com
· 2026-11-03
A reader poll of more than 1,200 respondents found over 60% believe Google Gemini's performance has declined in recent months, with complaints of misunderstandings and degraded output. Excluding non-users, nearly two-thirds of respondents reported dissatisfaction, while about 20% said they saw no decline and 14.6% were unsure. Commenters described Gemini as frustrating and said rival assistants now outperform it for everyday tasks.
androidauthority.com
· 2026-11-03
Anthropic has enabled 'message threads' by default for most Claude Code users, a feature that sends only changed data since the last turn instead of re-uploading the entire conversation history with each request. Anthropic reports this cuts time-to-first-token by a median of 35%, though total token usage and cost remain unchanged. API users can enable the feature manually via a 'thread' parameter.
zdnet.com
· 2026-11-03
Garry Tan, CEO of Y Combinator, told Walter Isaacson's podcast The Builders that he spends roughly $100,000 to $200,000 annually on AI tokens. Tan said he relies heavily on AI agents for work and personal tasks, including an agent that has read his email, Dropbox files and even two decades of therapy notes. He also described an internal YC agent called Stray Light that holds context on every founder the firm has backed.
techcrunch.com
· 2026-11-03
GoKawiil