Hacker News: zerop

New comment by zerop in "GPT-5.5"

zerop — Fri, 24 Apr 2026 08:57:43 +0000

So pelican must have become the mandatory test case to pass for all model providers before launch.

New comment by zerop in "Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B"

zerop — Mon, 06 Apr 2026 09:06:30 +0000

I have been looking forward to build something like this using open models. A voice assisstant I can talk while I am driving, as I do have long commute. I do use chatGPT voice mode and it works great for querying any information or discussions. But I want to do tasks like browsing web, act like a social media manager for my business etc.

Improving Interactive In-Context Learning from Natural Lang Feedback – DeepMind

zerop — Fri, 20 Feb 2026 10:21:19 +0000

Article URL: https://arxiv.org/abs/2602.16066

Comments URL: https://news.ycombinator.com/item?id=47086085

Points: 2

# Comments: 0

New comment by zerop in "Modular monolith and microservices: Modularity is what matters"

zerop — Mon, 10 Nov 2025 17:04:38 +0000

Microservices created the need for more teams, devs, coordination, meetings, scrum teams, scrum master, Jira, CI CD tools, cloud market and so on.. It is very well planned :)

America's dominance is over. By 2030, we'll have handful of global powers(2016)

zerop — Thu, 03 Apr 2025 13:14:05 +0000

Article URL: https://www.weforum.org/stories/2016/11/america-s-dominance-is-over/

Comments URL: https://news.ycombinator.com/item?id=43569130

Points: 4

# Comments: 1

New comment by zerop in "Tracing the thoughts of a large language model"

zerop — Thu, 27 Mar 2025 17:56:55 +0000

The explanation of "hallucination" is quite simplified, I am sure there is more there.

If there is one problem I have to pick to to trace in LLMs, I would pick hallucination. More tracing of "how much" or "why" model hallucinated can lead to correct this problem. Given the explanation in this post about hallucination, I think degree of hallucination can be given as part of response to the user?

I am facing this in RAG use case quite - How do I know model is giving right answer or Hallucinating from my RAG sources?

New comment by zerop in "Building AI agents to query your databases"

zerop — Tue, 18 Mar 2025 18:24:08 +0000

Thanks. sorry, asking more question - Do we need human in the loop with Cube to define the views for all kinds of queries.

In my use case, it's going to be exposed to various kind of stakeholders and there will be versatility of user queries. I can't pre-create views/aggregations for all scenarios.

New comment by zerop in "Building AI agents to query your databases"

zerop — Tue, 18 Mar 2025 15:40:59 +0000

Currently exploring cube for a "natural language to SQL" solution.

My schema is - 90+ Tables, 2500+ Columns, well documented

From your experience, does Cube look a fit? My use cases will definitely have JOINS.

New comment by zerop in "India's food shortage filled American libraries"

zerop — Wed, 01 Jan 2025 06:44:13 +0000

How people are unearthing knowledge from ancient libraries using Claude

https://x.com/PrintedPathways/status/1865637416637231406

New comment by zerop in "Show HN: I made a website to semantically search ArXiv papers"

zerop — Thu, 26 Dec 2024 12:13:50 +0000

This looks great, thanks for building this.

Something on similar lines which many may link, Research Rabbit - https://www.researchrabbit.ai/

New comment by zerop in "Moon"

zerop — Wed, 18 Dec 2024 16:07:24 +0000

Can we give reference of these articles to LLMs and get them to write articles like this for educational contents and produce similar WebGL graphics code to render images. I mean, just use this style and produce educational content using AI. that might make the studies more interesting.

New comment by zerop in "Moon"

zerop — Wed, 18 Dec 2024 16:07:15 +0000

New comment by zerop in "Ask HN: SWEs how do you future-proof your career in light of LLMs?"

zerop — Mon, 16 Dec 2024 15:37:25 +0000

I fear that in the goal of going from "manual coding" to "fully automated coding", we might end up in the middle, where we are "semi manual coding" assisted by AI, which would need different software engineer skill.

New comment by zerop in "Llama.cpp Now Supports Qwen2-VL (Vision Language Model)"

zerop — Sun, 15 Dec 2024 09:35:07 +0000

Is it possible to build similar to anthropic computer use feature with Qwen vision model.

Someone open sourced it with langchain

https://x.com/1littlecoder/status/1856397375704576399

AI Product Management

zerop — Fri, 13 Dec 2024 10:29:05 +0000

Article URL: https://www.deeplearning.ai/the-batch/issue-279/

Comments URL: https://news.ycombinator.com/item?id=42407431

Points: 84

# Comments: 42

New comment by zerop in "Show HN: DataFuel.dev – Turn websites into LLM-ready data"

zerop — Fri, 13 Dec 2024 04:50:09 +0000

Great, congrats on your launch.

1. Does it take care of Bot detection. Most sites will have it.

2. Is this something similar to Firecrawl - https://www.firecrawl.dev/

New comment by zerop in "Himalaya: CLI to Manage Emails"

zerop — Mon, 09 Dec 2024 14:59:16 +0000

Honest question - Why use interfaces like this, but not regular HTML client?

New comment by zerop in "The 70% problem: Hard truths about AI-assisted coding"

zerop — Fri, 06 Dec 2024 07:12:03 +0000

I fear that in the goal of going to "manual coding" to "fully automated coding", we might end up in the middle, where we are "semi manual coding" assisted by AI which needs different software engineer skill.

New comment by zerop in "Bringing K/V context quantisation to Ollama"

zerop — Thu, 05 Dec 2024 17:36:19 +0000

Many are there, apart from what others mentioned I am exploring Anything LLM - https://anythingllm.com/. Liked the workspace concept in it. We can club documents in workspaces and RAG scope is managed.

New comment by zerop in "Lessons from 15 Years of Indie App Development"

zerop — Sat, 30 Nov 2024 16:15:16 +0000

With the current advancement of AI in code generation, freelancers and Indies are going to have different trajectory than ever before