Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #21623

S

Supersimple

Company blog · supersimple.io/blogdataaistartups

Supersimple is the company blog at supersimple.io, writing about data, ai and startups. Since 2024, 3 different Hacker News readers have linked it 6 times, most often “First impressions of early-access GPT-4 fine-tuning”. No feed was found, so read it on the site itself.

No feed foundVisit the blog
6mentions?
3HN people?
2024–2024first – last linked?

Too few sampled comments (1) to say how often HN recommends it.?

Why HN links it

Blog post describing a startup's experience fine-tuning OpenAI LLMs to turn user requests into data explorations and reports, via a custom domain-specific language converted into UI.

Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Ask questions across your data warehouse and company knowledge. Get explainable answers built on governed definitions and permission-aware search.

Most-linked posts?

  1. First impressions of early-access GPT-4 fine-tuning
    3 people · 4 mentions · first linked 2024-03-19

What Hacker News says?

  1. We (a small startup) have recently seen considerable success fine-tuning LLMs (primarily OpenAI models) to generate data explorations and reports based on user requests. We provide relevant details of data schema as input and expect the LLM to generate a response written in our custom domain-specific language, which we then convert into a UI exploration. We've shared more details in a blog post: https://www.supersim…

    Comment linking /blog/gpt-4-fine-tuning-early-access

    on “Using GPT-4 fine-tuning to generate data explorations”
  2. Submitted First impressions of early-access GPT-4 fine-tuning as a story · 27 points

    HN discussion
  3. Submitted First Impressions of Early-Access GPT-4 Fine-Tuning as a story · 7 points

    HN discussion
  4. Submitted Why I Never Used Data as a Product Manager as a story · 4 points

    HN discussion
  5. Submitted Using GPT-4 fine-tuning to generate data explorations as a story · 4 points

    HN discussion
  6. Submitted Data Teams Shouldn't Be Firefighters as a story · 2 points

    HN discussion

Search all of HN for supersimple.io