Top all-time · #7057
deepsense.ai
Company blog · deepsense.ai/blog · on HN as Applied_AIaibusiness
deepsense.ai is the company blog at deepsense.ai, writing about ai and business. Since 2018, 11 different Hacker News readers have linked it 38 times, most often “Keras vs. PyTorch: Alien vs. Predator Recognition with Transfer Learning (2018)”. No feed was found, so read it on the site itself.
Too few sampled comments (8) to say how often HN recommends it.?
Why HN links it
HN commenters cite deepsense.ai posts on deep learning topics, including transfer learning, choosing Keras or PyTorch as a first framework, and multi-agent systems. The comments are mostly citations and self-references, with little direct judgment of the writing.
Summarised by Claude from a sample of 8 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
AI custom software development, enterprise AI solutions, and expert consulting. We specialize in LLMs, MLOps, computer vision, and AI-powered automation to drive business growth. Partner with us for cutting-edge AI integration and deployment.
Most-linked posts?
- Keras vs. PyTorch: Alien vs. Predator Recognition with Transfer Learning (2018)3 people · 4 mentions · first linked 2018-10-03
- Keras vs PyTorch2 people · 4 mentions · first linked 2018-06-28
- Outsmarting failure. Predictive maintenance powered by machine learning2 people · 2 mentions · first linked 2018-11-20
- Open Source or Custom in Enterprise AI Systems?2 people · 2 mentions · first linked 2026-05-13
What Hacker News says?
A few caveats here: - It works (that well) only for vision (for language it sort-of-works only at the word level: http://p.migdal.pl/2017/01/06/king-man-woman-queen-why.html ) - "Do Better ImageNet Models Transfer Better?" https://arxiv.org/abs/1805.08974 And if you want to play with transfer learning, here is a tutorial with a working notebook: https://deepsense.ai/keras-vs-pytorch-avp-transfer-learning/
Comment linking /keras-vs-pytorch-avp-transfer-learning/
on “The Unreasonable Effectiveness of Deep Feature Extraction”Submitted Keras vs PyTorch as a story · 385 points
HN discussionHaving worked with YOLO, I really recommend this intro: https://blog.paperspace.com/how-to-implement-a-yolo-object-d... . And in general, YOLO is performant and at the same time, it has a simpler architecture than the Fast(er) R-CNN family. And in general, due to its head, it is WAY more readable in PyTorch than in TensorFlow; to the point, I use it as an example in Keras vs PyTorch example https://deepsense.ai/kera…
Comment linking /keras-or-pytorch/
on “YOLO: Real-Time Object Detection”Submitted Building a Matrix with reinforcement learning and artificial imagination as a story · 14 points
HN discussionI wrote a whole article about that: "Keras or PyTorch as your first deep learning framework" ( https://deepsense.ai/keras-or-pytorch/ ). And it got somewhat popular here: https://news.ycombinator.com/item?id=17415321 (if you are curious of others' opinions). In short: don't learn (raw) TensorFlow as your first framework. Both TF-via-Keras and PyTorch are viable options, with their pros and cons.
Comment linking /keras-or-pytorch/
on “Facebook launches PyTorch 1.0”Submitted What is reinforcement learning? The complete guide as a story · 5 points
HN discussion>what would happen if you got LLM's to define the ontology. https://deepsense.ai/resource/ontology-driven-knowledge-grap... >hammering out an ontology for a particular area just results in a common understanding between those who wrote the ontology and a large gulf between them and the people they want to use it This is the other side of the bitter lesson, which is just the empirical observation of a phenomenon that…
Comment linking /resource/ontology-driven-knowledge-graph-for-graphrag/
on “CauseNet: Towards a causality graph extracted from the web”Submitted Open Source or Custom in Enterprise AI Systems? as a story · 4 points
HN discussionBasically these key factors: * are there any tutorials / code examples? (to see if I like its API/philosophy AND there is a way to pick it up) * are there any practical, working projects out there (used by companies, etc)? (otherwise it may be not useful for bigger projects) * is it in active development? (otherwise there is a risk that it will cease to be useful) * how does it match against other tools (e.g. maybe…
Comment linking /keras-or-pytorch/
on “Ask HN: What kind of information do you look for before learning/using new tech?”Submitted A framework for evaluating agentic AI systems as a story · 4 points
HN discussionFor a very practical introduction to deep learning with Keras, I recommend Deep Learning with Python by François Chollet, https://www.manning.com/books/deep-learning-with-python . For a general context, my post "Learning Deep Learning with Keras" https://p.migdal.pl/2017/04/30/teaching-deep-learning.html or for a practical quick start - "Starting deep learning hands-on: image classification on CIFAR-10" https://deep…
Comment linking /deep-learning-hands-on-image-classification/
on “Deep Learning Basics with Python, TensorFlow and Keras”Submitted We Built a 15-Agent System with Anthropic MCP: Here's When It Fails (and Shines) as a story · 4 points
HN discussionWe recently built a production-grade multi-agent system for document analysis using Anthropic’s Model Context Protocol (MCP). The system orchestrates 15+ agents with dynamic tool usage and task delegation. Here's the deep dive: https://deepsense.ai/blog/standardizing-ai-agent-integration... Key insights: 1. When MCP works best: - Multiple agents sharing tools/resources - Dynamic tool orchestration needs - Rapid prot…
Comment linking /blog/standardizing-ai-agent-integration-how-to-build-scalable-secure-and-maintainable-multi-agent-systems-with-anthropics-mcp/
on “We Built a 15-Agent System with Anthropic MCP: Here's When It Fails (and Shines)”Submitted Keras vs. PyTorch: Alien vs. Predator Recognition with Transfer Learning (2018) as a story · 4 points
HN discussionWe’re running a ~60-minute technical session (+Q&A) on what it takes to move AI agents beyond proof-of-concept. Our engineering teams at deepsense.ai have deployed multi-agent systems for clients in sports analytics, pharma, and telecom — including one that turned terabytes of football tracking data into a conversational knowledge base. Speakers: 1. Rafał Łabędzki, AI Engineering Manager — leads enterprise-scale age…
Comment linking /resource/ai-agents-lessons-learned-in-the-field/?utm_source=LinkedIn&utm_medium=Post_27_10_2025_HN&utm_campaign=AI_session
on “Most "AI agents" don't survive production – here's what works”Submitted Quick AI-related news digest (September edition) as a story · 4 points
HN discussionSubmitted Control Planes of Agentic AI Infrastructure for Reliable Software Delivery as a story · 3 points
HN discussionSubmitted AI Testing vs. Software Testing as a story · 3 points
HN discussionSubmitted Show HN: A practical framework for evaluating agentic AI systems as a story · 3 points
HN discussionSubmitted Top 5 AI trends 2019 (with cool infographic) as a story · 3 points
HN discussionSubmitted AI Monthly digest #2 – the fakeburger, BERT for NLP and machine morality as a story · 3 points
HN discussionSubmitted What breaks when AI-generated code reaches production systems as a story · 2 points
HN discussionSubmitted Most "AI agents" don't survive production – here's what works as a story · 2 points
HN discussionSubmitted Artificial Intelligence in dental health care as a story · 2 points
HN discussionSubmitted AI-Powered Movie Restoration as a story · 2 points
HN discussionSubmitted AI in supply chain management as a story · 2 points
HN discussionSubmitted Show HN: A practical AI Evaluation pattern as a story · 1 points
HN discussionSubmitted Show HN: EDA Benchmark Leaderboard as a story · 1 points
HN discussionSubmitted Engineers building MCPs in regulated industries: what's been the hardest part? as a story · 1 points
HN discussionSubmitted Lessons from testing GPT and Gemini native audio models for voice agents as a story · 1 points
HN discussion
