Hacker News: mikeqq2024

New comment by mikeqq2024 in "Ask HN: Who is hiring? (November 2025)"

mikeqq2024 — Thu, 13 Nov 2025 03:40:57 +0000

I got this instead "Instructions: Expected 'X-future' header with value 'automattician'", what did you get?

New comment by mikeqq2024 in "Ask HN: Where are the AI-driven profits or promotions?"

mikeqq2024 — Wed, 16 Jul 2025 08:08:02 +0000

The numbers does not make sense. "Over a dozen of them are public, and more than 100 are valued at $1 billion or more. More than 15,000 companies apply to get into the accelerator, with about a 1% acceptance rate."

New comment by mikeqq2024 in "Launch HN: BitBoard (YC X25) – AI agents for healthcare back-offices"

mikeqq2024 — Wed, 11 Jun 2025 08:55:01 +0000

same question for HIPAA compliance

New comment by mikeqq2024 in "Show HN: Plexe – ML Models from a Prompt"

mikeqq2024 — Sat, 10 May 2025 08:44:06 +0000

Could you elaborate usage about state transition libraries with agents further?

New comment by mikeqq2024 in "As an experienced LLM user, I don't use generative LLMs often"

mikeqq2024 — Fri, 09 May 2025 03:55:49 +0000

why not use /clear and /reset command?

New comment by mikeqq2024 in "Show HN: Vortex – a high-performance columnar file format"

mikeqq2024 — Tue, 15 Oct 2024 03:17:44 +0000

confusing indeed

New comment by mikeqq2024 in "Ask HN: Who's building an AI-free product?"

mikeqq2024 — Fri, 30 Aug 2024 02:22:40 +0000

can you elaborate further?

New comment by mikeqq2024 in "Exo: Run your own AI cluster at home with everyday devices"

mikeqq2024 — Fri, 26 Jul 2024 07:15:59 +0000

why there is no intel cpu/gpu support? it seems intel cpu/gpu is dead in AI community.

New comment by mikeqq2024 in "Insights from over 10,000 comments on "Ask HN: Who Is Hiring" using GPT-4o"

mikeqq2024 — Fri, 05 Jul 2024 06:20:05 +0000

Interesting that the job supply is highly co-relevant to interest rate. Thanks for sharing.

New comment by mikeqq2024 in "Insights from over 10,000 comments on "Ask HN: Who Is Hiring" using GPT-4o"

mikeqq2024 — Fri, 05 Jul 2024 06:06:07 +0000

Yes I also noticed nodejs is included in comparison with the JS frameworks.

New comment by mikeqq2024 in "Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser"

mikeqq2024 — Sun, 30 Jun 2024 03:48:31 +0000

1.8B/3.25B is still too much for edge devices. Ideally tens or hundreds mega would be ok. Is there an option to change the builtin Gemini Nano to other smaller models?

By the way, haven't touch the lastest JS code for a while, what does this new syntax mean: "import { chromeai } "

Also not get the textStream code: for await (const textPart of textStream) { result = textPart; } does result get override for each loop step?

New comment by mikeqq2024 in "Ask HN: What is the best code base you ever worked on?"

mikeqq2024 — Sat, 29 Jun 2024 15:14:20 +0000

One day I got an unexpected email from someone asking permission to use a piece of code on github I forgot I wrote almost 10 years ago without a license clause. I was very surprised and confused because I forgot I wrote that code, and I was not involving coding for quite some years and my github profile was blank without any contact information. I asked. It happened the guy simply made a search and found a post on a forum with my nickname, and email address - newly created recently. At that moment, it clicked and I felt some unusual arrangment. I quickly added an open source license, and the guy, CTO of a decent company, offered to make a donate. That made me a day.

New comment by mikeqq2024 in "Language models on the command line"

mikeqq2024 — Fri, 28 Jun 2024 05:10:14 +0000

There is similar ShellOracle: https://github.com/djcopley/ShellOracle

It is used as Bash widget, where you press CTL-F, describe your command, then press Enter, the generated command will be inserted into your shell prompt.

New comment by mikeqq2024 in "OpenEMR: Open-source medical record software"

mikeqq2024 — Fri, 28 Jun 2024 02:08:31 +0000

tech background here. Feel free to drop me a line if you need a teck parter to revamp what you described above

New comment by mikeqq2024 in "Show HN: FiddleCube – Generate Q&A to test your LLM"

mikeqq2024 — Thu, 27 Jun 2024 15:28:13 +0000

Is this done by calling gpt4o with user query, prompt and context to generate result as ground truth, and analysis? If so, what is the value added except perhaps automation?

New comment by mikeqq2024 in "My Windows Computer Just Doesn't Feel Like Mine Anymore"

mikeqq2024 — Tue, 25 Jun 2024 13:13:10 +0000

With help of codeLLM or shellLLM, that is no problem any more

New comment by mikeqq2024 in "Wc2: Investigates optimizing 'wc', the Unix word count program"

mikeqq2024 — Mon, 24 Jun 2024 05:32:16 +0000

Thanks for the detailed explanation to grok the whole landscape.

New comment by mikeqq2024 in "Why we no longer use LangChain for building our AI agents"

mikeqq2024 — Sun, 23 Jun 2024 13:31:34 +0000

Mind tell what kind of scenario you are tring to solve?

New comment by mikeqq2024 in "Why we no longer use LangChain for building our AI agents"

mikeqq2024 — Sun, 23 Jun 2024 13:08:22 +0000

Sql IS an API, as in android programming, you just use sql as an API to access SQLite, literally.

New comment by mikeqq2024 in "Why we no longer use LangChain for building our AI agents"

mikeqq2024 — Sun, 23 Jun 2024 09:32:27 +0000

What alternatives are you tring and how good/bad about those?