返回首页
最新
Hi HN, sorry for using a burner account.<p>It seems to me that up until the beginning of the last year, we saw a couple of new "open" model release announcements almost every week. They'd set a new state of the art for what an enthusiast could run on their laptop or home server.<p>Meta, Deepseek, Mistral, Qwen, even Google etc. were publishing new models left and right. There were new formats, quantizations, inference engines etc. and most importantly - a lot of discourse and excitement around them.<p>Quietly and suddenly, this changed. After the release of gpt-oss (August 2025), the discourse has been heavily dominated around hosted models now. I don't think I've seen any mention of Ollama in any discussion that reached HN's front page in the last 6 months.<p>What gives? Is this a proxy signal that we've hit a barrier in LLM efficiency?
Hi HN,<p>I built a simple tool called DeleteThreads (<a href="https://deletethreads.net/" rel="nofollow">https://deletethreads.net/</a>) to solve a personal annoyance: the lack of a "bulk delete" or "auto-archive" feature on Meta Threads.<p>If you've used the platform for a while, you've likely noticed there’s no way to clean up your history or prune old replies without doing it manually one by one.<p>What it does:<p>Bulk Delete: Mass remove posts and replies based on date filters.<p>Auto-Prune (The "Set and Forget" part): You can schedule a daily task to automatically delete posts older than X days (e.g., keeping only your last 30 days of activity).<p>It’s free to use for the core features. I'm an indie developer and would love to get your feedback on the UX or any technical features you'd like to see added.<p>Thanks!
Hi HN, I'm Kai Wang, one of the creators of Yuanzai World.<p>We built a simulation engine (currently on iOS & Android) that allows the community to create and share text adventures populated by multiple LLM-based agents. Unlike standard chatbots, our focus is on community co-creation—users define the worldviews, and our agents (with persistent memory and social relationships) bring them to life.<p>The cool part:<p>We implemented a system we call "World-Line Divergence" (inspired by visual novels like Steins;Gate). Usually, AI RPGs feel random or infinite loop. We built a state machine that tracks "World Deviation." If players interact with NPCs in specific ways (e.g., convincing an artist to change their style), it triggers a graph switch, leading to a completely different generated ending, effectively breaking the original script.<p>Tech Stack:<p>- Backend: Python / Java with a custom AI orchestration framework (to handle agent concurrency).<p>- Models: Hybrid routing between Gemini, GPT, and DeepSeek (optimizing for cost/performance based on task).<p>- Vector DB: Milvus (for handling long-term agent memory).<p>We are currently live on App Store and Google Play. Since it's a mobile-first experience, the link leads to our landing page where you can see the demo flow.<p>Would love to hear your feedback on the "World-Line" concept: Does this state-machine approach solve the aimlessness of AI RPGs?
Are you coding more or less, managing people differently, or making decisions in new ways because of AI tools? Which tools (LLMs, copilots, internal agents, analytics, etc.) have meaningfully stuck, and which turned out to be hype? I’m especially interested in concrete changes to how you plan, review work, and support teams.
I’m a solo founder running a two-sided marketplace app on the typical Vercel free tier + Supabase stack. It’s live with low-traffic right now. My concern is the 'cliff' I keep reading about—where Vercel becomes prohibitively expensive at scale. For those who migrated to a $5 Hetzner/DigitalOcean VPS:<p>What was the specific metric that forced the move? (Bandwidth, Function execution time, Cost?)<p>How much 'DevOps' time do you actually spend maintaining the VPS vs. building product?<p>I want to avoid premature optimization, but also don't want to be locked into a platform that will bankrupt the project if it takes off.