[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"posts-first-page-tooling-all":3},{"items":4,"nextCursor":91},[5,19,28,38,46,54,62,69,76,83],{"_id":6,"text":7,"link":8,"linkTitle":9,"linkImage":10,"tags":11,"feedId":15,"sourceName":16,"publishedAt":17,"likes":18},"6ad8cc821b3bf7b2b73df43f","Claude Mods are plugins written in TypeScript or JavaScript that run inside Claude Code, letting developers modify the CLI and desktop interface, observe events and change rendering or tool calls. This middleware approach lets you shape the agent's attention interface, making the AI more adaptable to individual engineering workflows.","https:\u002F\u002Fwww.latent.space\u002Fp\u002Fclaude-mods","Claude Mods let you customize Claude Code with TypeScript plugins","https:\u002F\u002Fres.cloudinary.com\u002Fdqjivljzi\u002Fimage\u002Fupload\u002Fv1792593025\u002Fdev-blog\u002Fpreviews\u002Ftlk4f0pktlbzcwz6yykq.png",[12,13,14],"ai","typescript","tooling","6aca13e059e75549a15c6fa5","Latent.Space","2026-10-21T13:04:19.000Z",0,{"_id":20,"text":21,"link":22,"linkTitle":23,"linkImage":24,"tags":25,"feedId":15,"sourceName":16,"publishedAt":27,"likes":18},"6ad85bff76cb3f9eca2238ec","Tenex pays AI engineers for delivered output rather than hours, aiming to align incentives as AI speeds up work. They keep story points for compensation but also consider non-ticket tasks like architecture design and customer context gathering. The model has scaled to a 75-person team serving Fortune 2000 and mid-market clients, highlighting how AI can reshape software development economics.","https:\u002F\u002Fwww.latent.space\u002Fp\u002Ftenex","Tenex experiments with output-based pay for AI-enhanced development","https:\u002F\u002Fres.cloudinary.com\u002Fdqjivljzi\u002Fimage\u002Fupload\u002Fv1792564222\u002Fdev-blog\u002Fpreviews\u002Fetf22hj7ujjguddqdpzk.jpg",[12,26,14],"frontend","2026-10-21T05:01:26.000Z",{"_id":29,"text":30,"link":31,"linkTitle":32,"linkImage":33,"tags":34,"feedId":35,"sourceName":36,"publishedAt":37,"likes":18},"6ad87ba475d61c1294d0d1fd","Cloudflare released Tsrs, a port of the TypeScript compiler written in Rust. The project aims to provide a faster compilation experience while keeping compatibility with existing TypeScript code. Developers interested in TypeScript performance or alternative toolchains may want to follow its progress.","https:\u002F\u002Fblog.cloudflare.com\u002Ftypescript-rust-port\u002F","Tsrs: TypeScript compiled to Rust","https:\u002F\u002Fres.cloudinary.com\u002Fdqjivljzi\u002Fimage\u002Fupload\u002Fv1792572323\u002Fdev-blog\u002Fpreviews\u002Fcxwicbnb2c6hzgqrdqiv.png",[13,14],"6aca13e059e75549a15c6fa3","Hacker News","2026-10-20T13:18:07.000Z",{"_id":39,"text":40,"link":41,"linkTitle":42,"linkImage":43,"tags":44,"feedId":35,"sourceName":36,"publishedAt":45,"likes":18},"6ad72a20a95de3849584d9d4","A Meta engineer shared concerns about relying on AI-generated code that feels like a black box, questioning how much understanding is needed before shipping. The discussion on Hacker News highlights the tension between rapid AI-assisted development and maintaining code comprehension, a relevant issue for developers using AI tools.","https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=50151036","Engineers discuss the challenges of shipping AI-generated code they don’t fully understand",null,[12,26,14],"2026-10-19T11:24:34.000Z",{"_id":47,"text":48,"link":49,"linkTitle":50,"linkImage":43,"tags":51,"feedId":35,"sourceName":36,"publishedAt":53,"likes":18},"6ad5843ebc308fd4ac90d973","A new paper introduces Hybrid Reasoning Agents, which combine latent-space reasoning with text-based actions. The authors provide code on GitHub and a Hugging Face collection, and include an evaluation section. Developers interested in AI-augmented tooling may find the approach useful for building more capable LLM-driven assistants.","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.18861","Hybrid Reasoning Agents: LLMs that reason in latent space and act via text",[12,52,14],"open-source","2026-10-18T20:48:14.000Z",{"_id":55,"text":56,"link":57,"linkTitle":58,"linkImage":43,"tags":59,"feedId":35,"sourceName":36,"publishedAt":61,"likes":18},"6ad52fe09adc3c655bcfd0d5","A new article on parser combinators was posted, discussing how they can be used to build composable parsers. The piece outlines the core concepts and shows examples that can be applied in JavaScript projects, offering an alternative to traditional parsing libraries.","https:\u002F\u002Ft3.at\u002Fblog\u002F2026-10-17-parser-combinators\u002F","Parser combinators explained",[60,14],"javascript","2026-10-18T08:19:53.000Z",{"_id":63,"text":64,"link":65,"linkTitle":66,"linkImage":43,"tags":67,"feedId":35,"sourceName":36,"publishedAt":68,"likes":18},"6ad4bf6035e08246c3192c08","DeepSeek announced a search and fetch API priced at $0.75 per 1,000 successful requests. The service offers a searchable interface for developers to integrate AI-driven retrieval into their applications, which could be useful for building smarter front-end features or tooling.","https:\u002F\u002Fapi-docs.deepseek.com\u002Fguides\u002Fsearch\u002F","DeepSeek launches search API with pay-per-request pricing",[12,14,60],"2026-10-18T06:50:36.000Z",{"_id":70,"text":71,"link":72,"linkTitle":73,"linkImage":43,"tags":74,"feedId":35,"sourceName":36,"publishedAt":75,"likes":18},"6ad513be880ffa5c3b9715fa","Sphinx is an open-source hook that integrates with existing AI coding agents. Each time code is pushed to production, it presents a questionnaire to verify the developer’s understanding of the changes before shipping. This adds a lightweight safety net for teams relying on AI-assisted development.","https:\u002F\u002Fsphinx-six-theta.vercel.app\u002F","Sphinx adds a pre-deployment questionnaire for AI-generated code",[12,14,52],"2026-10-18T04:33:49.000Z",{"_id":77,"text":78,"link":79,"linkTitle":80,"linkImage":43,"tags":81,"feedId":35,"sourceName":36,"publishedAt":82,"likes":18},"6ad432c2a351275aee265bc4","Pele is a tool that renders Mermaid diagrams as SVG files that can be styled with CSS themes. This makes diagram colors and fonts adaptable to dark mode or brand palettes without regenerating the diagram. Developers can integrate the SVG output into web pages or documentation pipelines and control appearance via standard stylesheet rules.","https:\u002F\u002Fpele.run\u002F","Pele introduces themeable SVG output for Mermaid diagrams",[26,14],"2026-10-17T15:55:09.000Z",{"_id":84,"text":85,"link":86,"linkTitle":87,"linkImage":88,"tags":89,"feedId":35,"sourceName":36,"publishedAt":90,"likes":18},"6ad3a621c272ca602ce735db","DeepSeek has published the V4.1 Flash model on Hugging Face, accessible via OpenRouter. The model is positioned as a lightweight, fast variant that may be useful for code-related tasks or quick prototyping. Developers interested in integrating AI assistance into their tooling can experiment with the model through the provided endpoints.","https:\u002F\u002Fhuggingface.co\u002Fdeepseek-ai\u002FDeepSeek-V4.1-Flash-1017","DeepSeek releases V4.1 Flash model on Hugging Face","https:\u002F\u002Fres.cloudinary.com\u002Fdqjivljzi\u002Fimage\u002Fupload\u002Fv1792255520\u002Fdev-blog\u002Fpreviews\u002Fy3gaapckzhazcft9mr1g.png",[12,52,14],"2026-10-17T08:21:25.000Z","MTc5MjIyNTI4NTAwMF82YWQzYTYyMWMyNzJjYTYwMmNlNzM1ZGI"]