Back to List
TechnologyAIBrowser ExtensionPrivacy

Tweeks (YC W25) Chrome Extension Leverages LLMs for Automated Userscript Generation, Sparks Debate on Privacy, Legality, and Open Source

Tweeks, a YC W25 Chrome extension, aims to 'de-enshittify' the web by automatically generating userscripts using Large Language Models (LLMs), similar to Greasemonkey/Tampermonkey. The extension captures current page content for LLM generation, with the resulting static scripts running locally. Key discussions revolve around technical feasibility, particularly with complex web structures and Manifest V3, and significant privacy concerns due to sending page content to LLMs during generation and the broad permissions required. Legal and platform risks, including potential site bans or lawsuits, are also central, with historical precedents like FB Purity cited. The business model and the extent of open-sourcing are debated, with the founders expressing caution about full open-source due to potential replication by larger entities. While users praise its ease of use for customization, the team acknowledges reliance on manual testing for accuracy and is exploring local small models for future cost and privacy improvements. The founders have disclosed DPA agreements with LLM providers regarding data retention and SOC II compliance.

News Hacker

Tweeks, a Chrome extension from YC W25, is designed to empower users to customize web pages by automatically generating userscripts through Large Language Models (LLMs). This functionality, akin to tools like Greasemonkey or Tampermonkey, aims to 'de-enshittify' the web. The process involves capturing the current web page content and sending it to an LLM for script generation. Once generated, these scripts operate statically and locally, applying to specific domains or patterns via `@match` rules.

The product has ignited extensive discussion across several critical areas. Technical feasibility is a major point, with concerns raised about the robustness of LLMs in handling complex web structures, deep nesting, iframes, and deliberately obfuscated CSS/JS. The team currently relies on a combination of manual testing and basic automated detection for script accuracy and selector matching, with many correctness validations still requiring manual regression testing. Future maintenance strategies include allowing users to pull updates, manually request selector updates, and the long-term vision of 'self-healing' scripts that periodically detect and fix selectors. Cross-browser portability is also a challenge, influenced by Manifest V3 and differences in browser extension APIs, making porting to Firefox or Safari non-trivial.

Privacy and permissions are central to the debate. Critics are concerned about data flow, as the founders admit that current page content is sent to the LLM during the 'generation' step. However, they clarify that generated scripts are static and execute locally, without passive logging. The extension requires broad page access permissions to run powerful scripts (reading/writing pages, notifications, localStorage), raising fears of permission abuse and malicious takeovers. The founders have stated they have Data Processing Agreements (DPAs) with LLM vendors that include non-training/non-retention clauses and claim SOC II compliance. However, a clause in their privacy policy regarding retaining the right to use generated scripts has been flagged as problematic and may be removed, with suggestions for greater transparency or open-sourcing to build trust.

The business model, open-source strategy, and investor concerns are also under scrutiny. Many question how Tweeks will monetize, as the founders acknowledge that a revenue model is not yet determined. There's a concern that widespread adoption could impact website revenue, making it difficult for Tweeks to directly capture that value. The community has repeatedly called for open-sourcing to protect user rights and prevent potential misuse if the company is acquired. However, the founders are cautious about full open-sourcing, fearing replication by larger companies for other purposes, and are leaning towards partial or gradual component release. The involvement of YC/VC funding is seen as enabling experimentation but also raises concerns about future acquisitions or commercialization potentially deviating from the product's original intent.

Legal and platform confrontation risks are significant. Historical precedents, such as the case of FB Purity, demonstrate that scripts modifying website appearance or functionality have faced platform bans or legal disputes. If Tweeks gains widespread adoption and significantly impacts platform revenue, large platforms could resort to legal and banning tactics to suppress such third-party tools. Some commentators believe that the actual impact might be overestimated due to limited general user adoption, while others warn of potential long-term legal battles. The startup team is advised to assess compliance risks and consider strategies like gentle modifications or communication with platforms to reduce the likelihood of direct conflict.

Related News

Technology

Google Unveils Antigravity: A New AI-Powered Autonomous Platform for End-to-End Software Development, Integrating with Gemini 3 for Agentic Coding

Google has launched Antigravity, a novel platform designed for "AI agent-led development," moving beyond traditional IDEs. This autonomous agent collaboration system enables AI to independently plan, execute, and verify complete software development tasks. Deeply integrated with the Gemini 3 model, Antigravity represents Google's key product in "Agentic Coding." It addresses limitations of previous AI tools, which were primarily assistive and required manual operation and step-by-step human prompts. Antigravity allows AI to work across editors, terminals, and browsers, plan complex multi-step tasks, automatically execute actions via tool calls, and self-check results. It shifts the development paradigm from human-operated tools to AI-operated tools with human supervision and collaboration. The platform's core philosophy revolves around Trust, Autonomy, Feedback, and Self-Improvement, providing transparency into AI's decision-making, enabling autonomous cross-environment operations, facilitating real-time human feedback, and allowing AI to learn from past experiences.

Technology

Google Vids Unlocks Advanced AI Features for All Gmail Users: Free Access to AI Voiceovers, Redundancy Removal, and Image Editing

Google has made several advanced AI features in its Vids video editing platform available to all users with a Gmail account, previously exclusive to paid subscribers. These newly accessible tools include AI voiceovers, automatic removal of redundant speech, and AI image editing. The transcription trimming feature automatically eliminates filler words like "um" and "ah," along with long pauses, significantly enhancing video quality. Users can also generate professional-grade voiceovers from text scripts, choosing from seven different voice options, many of which sound natural. Additionally, the AI image editing tool allows for easy modifications such as background removal, descriptive editing, and transforming static photos into dynamic videos. Google aims to empower both beginners and experienced creators to produce high-quality video content, anticipating significant growth in the video editing market despite Vids being in its early stages.

Technology

Quora's Poe AI Platform Launches Group Chat Feature Supporting Up to 200 Users for Enhanced Collaborative AI Interactions

Quora has introduced a new group chat feature for its AI platform, Poe, allowing up to 200 users to collaborate with various AI models and bots in a single conversation. This innovation supports multi-modal interactions including text, image, video, and audio generation. The launch coincides with OpenAI's ChatGPT piloting similar group chat functionalities in select markets, signaling a shift in AI interaction methods. Quora highlights that this feature will offer new interactive experiences for AI users, such as family trip planning using Gemini 2.5 and o3Deep Research, or team brainstorming with image models to create mood boards. Users can also engage in intellectual games with Q&A bots. Group chats can be created from Poe's homepage, with real-time synchronization across devices, ensuring seamless transitions between desktop and mobile. Quora developed this feature over six months and plans to optimize it based on user feedback, emphasizing the unexplored potential for group interaction and collaboration in AI mediums. Poe also enables users to create and share custom bots.