Top all-time · #10296
P. Galeone
Personal blog · pgaleone.eu · on HN as me2tooprogrammingai
P. Galeone's personal blog at pgaleone.eu covers programming and ai. Since 2017, 7 different Hacker News readers have linked it 44 times, most often “Use Your Brain: Engineering Standards in the Age of LLM”. It is still writing: the last post was on 2026-10-20, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
Linked for a post by the author on using AI for coding with Cline and LLMs. The only comment here questions the technical soundness of one code example in that post.
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.
Let the machines learn
Most-linked posts?
- Use Your Brain: Engineering Standards in the Age of LLM2 people · 3 mentions · first linked 2026-07-26
- Getting Back to the EU: From Google Cloud to Self-Hosted EU Infrastructure2 people · 2 mentions · first linked 2025-03-15
- Tensorflow 2.0: models migration and new design2 people · 2 mentions · first linked 2018-11-04
What Hacker News says?
But the API is strictly statically typed in reality. The core is written in C++ and every operation requires a well-known type in input. As you can see from the error raised in this example: https://pgaleone.eu/tensorflow/go/2017/05/29/understanding-t...
Comment linking /tensorflow/go/2017/05/29/understanding-tensorflow-using-go/
on “Tensorflow 2.0: models migration and new design”Submitted Tensorflow 2.0: models migration and new design as a story · 246 points
HN discussionI find it strange that the author is really happy with the quality of string comparison here https://pgaleone.eu/ai/coding/2025/01/26/using-ai-for-coding... and while it would kind of work, it's a very weird piece of code from ML standpoint, e.g. it's training a TF-IDF vectorizer on just two strings being compared, which at best won't change anything (unless the same word is repeated within one product), and is a su…
Comment linking /ai/coding/2025/01/26/using-ai-for-coding-my-experience/
on “Using AI for Coding: My Journey with Cline and LLMs”Submitted Using AI for Coding: My Journey with Cline and LLMs as a story · 198 points
HN discussionYup! I realized it. I wrote that because in the past there was a huge problem with the operators, as I explained in this talk: https://pgaleone.eu/tf-function-talk/#slide=28 Even if now autograph is able to convert them correctly, I still prefer to have every operator explicitly converted whenever possibile. The loop, luckily, never had this transpilation problems
Comment linking /tf-function-talk/
on “Advent of Code 2021 in pure TensorFlow – day 1”Submitted Advent of Code 2021 in pure TensorFlow – day 1 as a story · 80 points
HN discussionI wrote something very related to this: https://pgaleone.eu/ai/2026/07/26/use-your-brain/
Comment linking /ai/2026/07/26/use-your-brain/
on “AI doesn't generate working products, that's still your job”Submitted LLMs are making me lose my savviness as a story · 60 points
HN discussionSubmitted Getting Back to the EU: From Google Cloud to Self-Hosted EU Infrastructure as a story · 10 points
HN discussionSubmitted Getting Back to the EU: From Google Cloud to Self-Hosted EU Infrastructure as a story · 6 points
HN discussionSubmitted Use Your Brain: Engineering Standards in the Age of LLM as a story · 4 points
HN discussionSubmitted Advent of Code 2021 in pure TensorFlow – day 12 as a story · 3 points
HN discussionSubmitted Gitlab CI/CD for cross-platform Unreal Engine 4 projects as a story · 3 points
HN discussionSubmitted Tensorflow 2.0: Keras is not (yet) a simplified interface to Tensorflow as a story · 3 points
HN discussionSubmitted Tensorflow 2.0: models migration and new design as a story · 3 points
HN discussionSubmitted Use Your Brain: Engineering Standards in the Age of LLMs as a story · 2 points
HN discussionSubmitted Fixing the code signing and notarization issues of Unreal Engine (5.3) projects as a story · 2 points
HN discussionSubmitted The (Hidden?) Costs of Vertex AI Resource Pools: A Cautionary Tale as a story · 2 points
HN discussionSubmitted Third-party library as Unreal Engine plugin: ABI compatibility issues on Linux as a story · 2 points
HN discussionSubmitted FaceCTRL: Control your media player with your face as a story · 2 points
HN discussionSubmitted Analyzing tf.function to discover AutoGraph strengths and subtleties as a story · 2 points
HN discussionSubmitted Understanding Tensorflow using Go as a story · 2 points
HN discussionSubmitted EGPU and Local LLM Inference as a story · 1 points
HN discussionSubmitted Malvertising and the trend of curl – sh install on macOS as a story · 1 points
HN discussionSubmitted Digital Excommunication as a story · 1 points
HN discussionSubmitted Gemini-Powered Stock Analysis: Parsing Financial News for Trading Decisions as a story · 1 points
HN discussionSubmitted Vertex AI to Google Gen AI SDK: Service Account Authentication for Python and Go as a story · 1 points
HN discussionSubmitted Building a RAG for Tabular Data in Go with PostgreSQL and Gemini as a story · 1 points
HN discussionSubmitted Using Gemini in a Go application: limits and details as a story · 1 points
HN discussionSubmitted Custom model training and deployment on Google Cloud using Vertex AI in Go as a story · 1 points
HN discussion