Hacker News: pplonski86

Build a Web App for Your Machine Learning Model

pplonski86 — Fri, 12 Jun 2026 11:43:34 +0000

Article URL: https://mljar.com/blog/web-app-machine-learning/

Comments URL: https://news.ycombinator.com/item?id=48502867

Points: 2

# Comments: 0

Show HN: A curated collection of simple datasets for machine learning

pplonski86 — Wed, 10 Jun 2026 14:10:41 +0000

Article URL: https://github.com/pplonski/datasets-for-start

Comments URL: https://news.ycombinator.com/item?id=48476571

Points: 4

# Comments: 1

Show HN: Impress your boss with interactive Decision Tree Visualization

pplonski86 — Wed, 10 Jun 2026 10:34:44 +0000

Article URL: https://github.com/mljar/supertree

Comments URL: https://news.ycombinator.com/item?id=48474249

Points: 5

# Comments: 0

Show HN: SuperTree – interactive decision tree plot for sklearn,xgboost,lightgbm

pplonski86 — Tue, 09 Jun 2026 08:54:21 +0000

Article URL: https://github.com/mljar/supertree

Comments URL: https://news.ycombinator.com/item?id=48458471

Points: 2

# Comments: 0

Why ipynb is a perfect format for saving AI data analysis conversations

pplonski86 — Fri, 29 May 2026 08:41:54 +0000

Article URL: https://mljar.com/blog/why-ipynb-is-perfect-format-for-saving-ai-data-analysis-conversations/

Comments URL: https://news.ycombinator.com/item?id=48320664

Points: 1

# Comments: 0

Show HN: Mercury v3 – Convert Python Notebooks to Web Apps

pplonski86 — Mon, 25 May 2026 08:39:07 +0000

Article URL: https://github.com/mljar/mercury

Comments URL: https://news.ycombinator.com/item?id=48264716

Points: 2

# Comments: 0

New comment by pplonski86 in "Launch HN: Superset (YC P26) – IDE for the agents era"

pplonski86 — Fri, 22 May 2026 15:59:00 +0000

is it terminal on steroids some kind of? so you can manage mutiple coding agents? how many coding agents you can manage in parallel that it is still comfortable to work and code changes are meaningful

Show HN: Mercury v3 – Convert Python Notebooks to Web Apps

pplonski86 — Fri, 22 May 2026 14:32:03 +0000

Article URL: https://github.com/mljar/mercury

Comments URL: https://news.ycombinator.com/item?id=48236428

Points: 2

# Comments: 0

AI Generated Code Looked Right, but the Data Was Wrong

pplonski86 — Thu, 21 May 2026 11:21:49 +0000

Article URL: https://mljar.com/blog/ai-generated-code-looked-right-data-was-wrong/

Comments URL: https://news.ycombinator.com/item?id=48220828

Points: 2

# Comments: 0

Insurance Pricing – compare TabPFN 3.0 vs. classic ML

pplonski86 — Thu, 21 May 2026 10:46:07 +0000

Article URL: https://oleksandrruppelt.substack.com/p/insurance-pricing-with-tabpfn-30

Comments URL: https://news.ycombinator.com/item?id=48220509

Points: 2

# Comments: 0

New comment by pplonski86 in "Int a = 5; a = a++ + ++a; a =? (2011)"

pplonski86 — Thu, 14 May 2026 19:09:34 +0000

I love such puzzles! I used to use a lot ternary operators in C++ but one day friend of mine told me that I shouldn't nest ternary operators too much because code is too complicated to read - he understands code perfectly, he was just worried about younger programmers. Since then I started to use longer versions of code instead of smart shortcuts - to improve readability of code.

New comment by pplonski86 in "AI is making me dumb"

pplonski86 — Thu, 14 May 2026 19:04:32 +0000

before I ask AI to write anything, I prepare a plan, I was very positively surprised when noticed Plan mode in Codex recently. It make me feel that maybe others doing the same and that's why they added it. Anyway, I start with plan, then ask AI to do just one step.

If coding a new feature, I do one step and check the code, doing git diff, reading changes, or just asking Codex, to show me changes.

If writing an article, I ask for only one paragraph. I read paragraph and if it is ok, I accept it, if it doesn't show off my thoughts I work on one paragraph.

If doing data analysis with AI, I do one step of analysis and ask AI to display intermediate results so I can see if all is going in good direction and there are no hallucinations, additionally I have follow-up prompts for AI to do results verification. If all looks good, then I continue to the next step.

I don't like situation when I ask AI to do all code changes, or all article, or all data analysis in one pass with one prompt. It is simply impossible to check if AI is correct and results are not satisfactory. You can easily see this when asking AI to write a deep article with one prompt - you clearly see that it doesn't reflect your thoughts.

Maybe step-by-step is the approach to use AI and not feel dumber.

The Main Path to Creative AI

pplonski86 — Tue, 12 May 2026 18:50:53 +0000

Article URL: https://danielmiessler.com/blog/the-main-path-to-truly-creative-ai

Comments URL: https://news.ycombinator.com/item?id=48112612

Points: 2

# Comments: 0

New comment by pplonski86 in "If AI writes your code, why use Python?"

pplonski86 — Tue, 12 May 2026 14:02:28 +0000

Python outputs is also very versatile. You can use Python to build command line script, web application, desktop app with GUI, notebook with data analysis, or Python package and share with others. It is many ways how Python code can be used by final user.

New comment by pplonski86 in "Ask HN: What are you working on? (May 2026)"

pplonski86 — Mon, 11 May 2026 09:52:22 +0000

Im working on AI data analyst - MLJAR Studio. It is conversational UI with AI agent which uses Python to provide data insights. It is available as desktop application https://mljar.com

New comment by pplonski86 in "AI Generated Code Looked Right, but the Data Was Wrong"

pplonski86 — Tue, 05 May 2026 08:33:24 +0000

I'm working on an AI Data Analyst in MLJAR Studio and found this small but interesting bug while testing a medical data use case. The AI-generated Pandas code looked correct and executed without errors, but the dataframe was misaligned. The first patient had 148 pregnancies because glucose values were shifted into the Pregnancies column. The interesting part for me was that the bug was caught only because both the displayed dataframe and an extra LLM output checking step were reviewed.

AI Generated Code Looked Right, but the Data Was Wrong

pplonski86 — Tue, 05 May 2026 08:32:27 +0000

Article URL: https://mljar.com/blog/ai-generated-code-looked-right-data-was-wrong/

Comments URL: https://news.ycombinator.com/item?id=48019600

Points: 1

# Comments: 1

New comment by pplonski86 in "Show HN: Mljar Studio – local AI data analyst that saves analysis as notebooks"

pplonski86 — Tue, 05 May 2026 07:14:42 +0000

Thank you! I will check them out. It is worth to mention that MLJAR Studio is a desktop application, which is easy to install. It is running locally, and support local LLMs so all data stay safe.

New comment by pplonski86 in "Show HN: Mljar Studio – local AI data analyst that saves analysis as notebooks"

pplonski86 — Mon, 04 May 2026 14:14:42 +0000

User is not touching notebook at all, user just ask questions in natural language, and AI is using Python to compute answer, the ipynb notebook format is used to save the conversation.

New comment by pplonski86 in "Show HN: Mljar Studio – local AI data analyst that saves analysis as notebooks"

pplonski86 — Mon, 04 May 2026 08:28:17 +0000

Human in the loop in data analysis is really challenging task. We provide Python code for inspection, so user can check details how results were produced. Additionally, we run AI on results - user need to check the outputs and AI provided insights.