AI assistants fail on complex interview-style interactions

“Show HN: Local task classifier and dispatcher on RTX 3080 Hi HN, I am shubham a 3d artist who learned coding in college as an I.T. graduate know logics but not an expert as i just wanna try my hands on to ai So i built Resilient Workflow Sentinel this is offline ai agent which classify urgency (Low,Medium and HIgh) and dispatches to the candidates based on availability Well i want an offline system like a person can trust with its sensitive data to stay completely locally Did use ai to code for ”

“Ask HN: What weird or scrappy things did you do to get your first users? Hi everyone, I’m building Persona, a platform to delegate email scheduling to AI. Lately, I’ve been working hard to get those first users on board, but it’s been quite challenging. I’ve already tried the typical strategies that everybody talks about: cold email, LinkedIn InMail, careful targeting, decent copy. It’s mostly been a dead end. Low open rates, almost no replies. At this point, I’m not looking for the usual advice”

“Show HN: Open-source AI assistant for interview reasoning I built an open source desktop AI assistant after getting frustrated with how brittle most tools feel once questions go beyond basic Q and A. The goal was to explore whether an assistant could reliably handle interview style interactions such as system design discussions, multi step coding problems, and deeper follow up questioning without hiding behavior behind a closed SaaS. The assistant supports both cloud and local LLMs, uses a bring”

“Ask HN: Who's hiring but companies that don't have AI mandates? I'm looking for companies that don't have AI mandates. I suppose this can be interpreted in two ways: - no mandate that forces the use of AI (employees are free to use them or not at their discretion and team dynamics) - or the opposite, a mandate to enforce that AI should not be used (I suspect this will be even rarer?)”

“Ask HN: Article to share with a technical manager about modern AI coding tools? I’m on an IT team, and my manager uses ChatGPT’s chat interface for some tasks, (IAC) so he’s generally aware of AI. However, he’s not familiar with more advanced tools like Claude Code, Codex, or other development tools. I’m looking for a, balanced article that explains: What these tools can realistically do today Where they still struggle or fall short Any recommendations?”

“Ask HN: How are you doing technical interviews in the age of Claude/ChatGPT? I’m a founder/dev trying to figure out a better way to do technical interviews, because the current state is a nightmare. Right now, every standard take-home or HackerRank/LeetCode test is easily solved by LLMs. As a result, companies are accidentally hiring what we call vibe coders, candidates who are phenomenal at prompting AI to generate boilerplate, but who completely freeze when the architecture gets comp”