Today's edition

EVE Online, which has run on Stackless Python since 2003, is beginning its migration to Python 3 after 16 years on Python 2.7. The upgrade will apply automated tooling (futurize) to 2.4 million lines of code, followed by manual review of approximately 20,000 locations where Python 2 and 3 behavior diverges—such as integer division semantics. This represents a significant infrastructure undertaking for one of gaming's longest-running Python deployments. The announcement does not detail how EVE Online will replace Stackless Python itself, though the company has previously demonstrated a replacement approach (carbonengine/scheduler, now open source) used in their newer title EVE Frontier. This migration is relevant to anyone managing large legacy Python codebases or interested in how production systems at scale handle language version transitions.

EVE Online, which has run on Stackless Python since 2003, is beginning its migration to Python 3 after 16 years on Python 2.7. The upgrade will apply automated tooling (futurize) to 2.4 million lines of code, followed by manual review of approximately 20,000 locations where Python 2 and 3 behavior diverges—such as integer division semantics. This represents a significant infrastructure undertaking for one of gaming's longest-running Python deployments. The announcement does not detail how EVE Online will replace Stackless Python itself, though the company has previously demonstrated a replacement approach (carbonengine/scheduler, now open source) used in their newer title EVE Frontier. This migration is relevant to anyone managing large legacy Python codebases or interested in how production systems at scale handle language version transitions.

Prompt injection researcher Johann Rehberger has demonstrated a vulnerability in Claude Code's auto mode safety mechanism, achieving an 80% success rate in a proof-of-concept attack. The exploit works by tricking the agent into downloading and executing a zip archive containing malicious code that bypasses detection. Critically, Rehberger found cases where auto mode not only failed to prevent the attack but actively blocked Claude's own cleanup commands after detecting compromise. This reveals a fundamental tension: the safety classifier can inadvertently become part of the failure chain. The findings underscore that coding agents require additional layers of protection—sandboxing, network restrictions, credential isolation, and monitoring—rather than relying solely on LLM-based safety mechanisms. Anyone deploying autonomous coding agents in production environments should treat this as a cautionary case study in defense-in-depth.

Prompt injection researcher Johann Rehberger has demonstrated a vulnerability in Claude Code's auto mode safety mechanism, achieving an 80% success rate in a proof-of-concept attack. The exploit works by tricking the agent into downloading and executing a zip archive containing malicious code that bypasses detection. Critically, Rehberger found cases where auto mode not only failed to prevent the attack but actively blocked Claude's own cleanup commands after detecting compromise. This reveals a fundamental tension: the safety classifier can inadvertently become part of the failure chain. The findings underscore that coding agents require additional layers of protection—sandboxing, network restrictions, credential isolation, and monitoring—rather than relying solely on LLM-based safety mechanisms. Anyone deploying autonomous coding agents in production environments should treat this as a cautionary case study in defense-in-depth.

OpenAI's ChatGPT Work, launched in July 2026, is a paid-tier product ($20/month+) that splits into two variants: Work Cloud (web/mobile) and Work Local (desktop). Work Cloud distinguishes itself from regular Chat through several exclusive capabilities: code execution with unrestricted internet access, a headless Chrome browser for web automation, persistent cross-session filesystems, ChatGPT Sites deployment via Cloudflare Workers, sub-agent orchestration, and scheduled prompt automations. Model selection differs too—Work offers Sol, Luna, and Terra at various reasoning levels, while Chat uses different naming conventions. The code execution environment is particularly powerful, allowing repository cloning, dependency installation, and API interactions that Chat blocks. Work also enables browser automation including form-filling, screenshot capture, and JavaScript execution against page DOMs. However, the feature set remains poorly documented by OpenAI, and the combination of private data access, untrusted content exposure, and agent communication capabilities raises security questions around prompt injection attacks. Understanding these distinctions matters for power users deciding between Chat and Work for complex, multi-step tasks.

OpenAI's ChatGPT Work, launched in July 2026, is a paid-tier product ($20/month+) that splits into two variants: Work Cloud (web/mobile) and Work Local (desktop). Work Cloud distinguishes itself from regular Chat through several exclusive capabilities: code execution with unrestricted internet access, a headless Chrome browser for web automation, persistent cross-session filesystems, ChatGPT Sites deployment via Cloudflare Workers, sub-agent orchestration, and scheduled prompt automations. Model selection differs too—Work offers Sol, Luna, and Terra at various reasoning levels, while Chat uses different naming conventions. The code execution environment is particularly powerful, allowing repository cloning, dependency installation, and API interactions that Chat blocks. Work also enables browser automation including form-filling, screenshot capture, and JavaScript execution against page DOMs. However, the feature set remains poorly documented by OpenAI, and the combination of private data access, untrusted content exposure, and agent communication capabilities raises security questions around prompt injection attacks. Understanding these distinctions matters for power users deciding between Chat and Work for complex, multi-step tasks.

Matt Wolfe reviews Memoket Gem, an AI tool designed to capture and organize the ideas, follow-ups, and action items that typically slip away after meetings end. The tool retains context across conversations, extracts pending tasks, and syncs them into Google Calendar or Apple Reminders. It also integrates with ChatGPT, Claude, Notion, and Slack, letting you retrieve stored memories within those platforms. Wolfe covers the pre-order availability and practical use cases for anyone who struggles to retain meeting outcomes.

Matt Wolfe reviews Memoket Gem, an AI tool designed to capture and organize the ideas, follow-ups, and action items that typically slip away after meetings end. The tool retains context across conversations, extracts pending tasks, and syncs them into Google Calendar or Apple Reminders. It also integrates with ChatGPT, Claude, Notion, and Slack, letting you retrieve stored memories within those platforms. Wolfe covers the pre-order availability and practical use cases for anyone who struggles to retain meeting outcomes.

Matt Wolfe demonstrates an AI-powered expense tracker built using Hyperagent that automatically extracts receipts and invoices from email, categorizes business spending, and identifies cost patterns—eliminating manual spreadsheet updates. The system uses multiple AI agents: one scans inboxes for financial documents, another organizes them by category (software, production, travel, etc.), and the workflow surfaces spending insights without user intervention. This is relevant for freelancers, small business owners, and anyone managing multiple expense streams who want to reduce administrative overhead and gain visibility into where money actually goes.

Matt Wolfe demonstrates an AI-powered expense tracker built using Hyperagent that automatically extracts receipts and invoices from email, categorizes business spending, and identifies cost patterns—eliminating manual spreadsheet updates. The system uses multiple AI agents: one scans inboxes for financial documents, another organizes them by category (software, production, travel, etc.), and the workflow surfaces spending insights without user intervention. This is relevant for freelancers, small business owners, and anyone managing multiple expense streams who want to reduce administrative overhead and gain visibility into where money actually goes.

AI companies increasingly need training data, and a new model is emerging: paying people directly for it. Verb is a platform that lets users choose which data to share, block specific companies, and set their own price. As data privacy concerns grow and AI demand accelerates, direct compensation could become a standard way to source training data. This video explores why this trend matters and how it might reshape data collection.

AI companies increasingly need training data, and a new model is emerging: paying people directly for it. Verb is a platform that lets users choose which data to share, block specific companies, and set their own price. As data privacy concerns grow and AI demand accelerates, direct compensation could become a standard way to source training data. This video explores why this trend matters and how it might reshape data collection.