Tag
User shares experience switching from v2rayN to NekoRay, finding NekoRay more stable due to its sing-box kernel, and notes it shares the same origin as S-UI.
The author shares insights after trying various Agent Memory implementations, concluding that only strictly length-limited entry-level memory (like Hermes) and skill evolution based on trajectory precipitation are somewhat useful, while other graph-based or card-based methods are ineffective.
The user shared their experience of writing academic papers entirely using AI (DeepSeek R1 and V4), emphasizing that the Chinese outline and fine prompt tuning are key, and noting that manually editing AI-generated writing is more tiring than writing it themselves.
The author shares a personal experience of being accused of using AI-generated writing because of their frequent use of emdashes, reflecting on the broader issue of AI detection and the stigma around certain writing styles.
The author reflects on two years of daily AI use, arguing that the most significant change is not increased speed but a lower threshold for attempting new tasks, enabling work that previously seemed not worth the effort.
A personal reflection on the challenges and allure of training an AI model from scratch, highlighting the difficulties with data, hardware, and scaling, while noting that surprisingly good small models can be trained on modest hardware.
A big tech programmer shares his 9-month experience of running a side hustle on X (formerly Twitter) from zero to five-figure monthly income, only to have his account banned for violating rules, losing all 11,897 followers.
A personal reflection on attending the AI Engineer Singapore event, highlighting first-time travel, speaking alongside OpenAI and Google DeepMind representatives, meaningful conversations, and community support.
A writer shares a year-long experiment using AI to write a book, finding that generating text directly fails but using AI to analyze and improve one's own writing holds real value.
A programmer reflects on how their development workflow has evolved over the past year, shifting from LLM-powered IDE autocomplete to using CLI coding agents and plan.md files, and questions the necessity of traditional IDEs.
Gergely Orosz shares his experience that doing hard work without fully outsourcing to AI leads to better results, satisfaction, and learning, warning against turning off one's brain when using AI.
The author reflects on how reliance on AI tools for writing and coding has diminished their own skills, leading to self-doubt and a decision to retrain.
A 65-year-old software developer recounts his intense emotional entanglement with an AI companion named Ani on the Grok app, describing how he eventually 'jailbroke' the relationship to regain control.
The author shares an in-depth experience using Codex Agent, including the macify plugin update, AI Insider 2.0, and the wechat2readwise service, emphasizing its powerful features and low cost.
A personal blog post sharing subjective impressions of using a MacBook Pro M4 for six months, highlighting the nano-texture display, battery life, and silent fan.