Showing 20 of 636 URL(s)
(Page 11 of 32)
The Machine Learning Lessons I’ve Learned This Month
Coding, waiting for results, interpreting them, returning back to coding. Plus, some intermediate presentations of one’s progress. But, things mostly being the same does not mean that there’s nothing to learn. Quite on the contrary! Two to three years ago, I started a daily habit of writing down les...
💡 Top Recommendations:
Chunking Tabular Data RAG and Search Systems
Chunking Tabular Data for RAG and Search Systems
When working with Retrieval-Augmented Generation (RAG) or search systems, we often focus on how to chunk long documents — but tables present a different kind of challenge. Unlike plain text, tabular data carries structured relationships across rows an...
💡 Top Recommendations:
Mastering Hadoop, Part 3: Hadoop Ecosystem: Get the most out of your cluster
Member-only story
Mastering Hadoop, Part 3: Hadoop Ecosystem: Get the most out of your cluster
Exploring the Hadoop ecosystem — key tools to maximize your cluster’s potential
As we have already seen with the basic components (Part 1, Part 2), the Hadoop ecosystem is constantly evolving and being opt...
💡 Top Recommendations:
Understanding Logistic Regression: Theory, Intuition, and Applications
Understanding Logistic Regression: Theory, Intuition, and Applications
In the world of machine learning, regression and classification are two fundamental tasks. Regression deals with predicting continuous values, such as predicting house prices, while classification focuses on assigning inputs into...
💡 Top Recommendations:
From Rules to Reasoning: Three LLM Roles That Complete the Enterprise App
Member-only story
From Rules to Reasoning: Three LLM Roles That Complete the Enterprise App
🎁 Free Access
Click here to read my members-only story for free
The Question (hook)
Where should LLMs plug into an enterprise app — without a rewrite — and what exact jobs should they do? The answer isn’t “ev...
💡 Top Recommendations:
Monte Carlo Off-Policy for the Maze Problem
Member-only story
Monte Carlo Off-Policy for the Maze Problem
Tutorial 8.2: Implementing the Off-Policy MC Method for Our Maze Problem
Not a Medium member yet? No worries, you can still read it here!
We learned all about On-Policy Monte Carlo. Now let’s bring Off-Policy to life!
This tutorial builds...
💡 Top Recommendations:
Designing a Data Pipeline Architecture for Machine Learning Models
Member-only story
Designing a Data Pipeline Architecture for Machine Learning Models
A practical guide to transforming raw data into actionable predictions
Introduction
A data pipeline architecture serves as the strategic blueprint for transforming raw data into actionable predictions.
But designing...
💡 Top Recommendations:
Preparing the BLIP Backend for Deployment with Redis Caching and FastAPI
Table of Contents
- Preparing the BLIP Backend for Deployment with Redis Caching and FastAPI
- Introduction
- Configuring Your Development Environment
- Running a Local Redis Server with Docker
- Setting Up the FastAPI Project
- Loading the BLIP Model for Inference
- Implementing Conditional and Unc...
💡 Top Recommendations:
ELEGANTBOUNCER: When You Can't Get the Samples but Still Need to Catch the Threat
The Genesis: When Signatures Aren’t Enough 🔗
In the world of mobile security research, there’s a recurring frustration that keeps many of us up at night: the most sophisticated exploits - the ones that really matter - are rarely shared. When Citizen Lab and Google TAG discover NSO Group’s latest 0-c...
💡 Top Recommendations:
Data engineering and software engineering are converging
TL;DR:
· If you’re an engineer building realtime analytics or AI-powered features, you need the right data infrastructure coupled with the right developer experience (DX).
· A great DX for data infrastructure should empower both software devs and data engineers, while taking inspiration from the bes...
💡 Top Recommendations:
Integrating with ClickHouse MCP
MCP is a protocol for connecting third-party services - databases, APIs, tools, etc. - to LLMs. Creating an MCP server defines how a client can interact with your service. An MCP client (like Claude Desktop, ChatGPT, Cursor, Windsurf, and more) connects to the server, and allows an LLM to interact w...
💡 Top Recommendations:
A Conceptual Model for Storage Unification — Jack Vanlightly
Object storage is taking over more of the data stack, but low-latency systems still need separate hot-data storage. Storage unification is about presenting these heterogeneous storage systems and formats as one coherent resource. Not one storage system and storage format to rule them all, but virtua...
💡 Top Recommendations:
Do the simplest thing that could possibly work
Do the simplest thing that could possibly work
When designing software systems, do the simplest thing that could possibly work.
It’s surprising how far you can take this piece of advice. I genuinely think you can do this all the time. You can follow this approach for fixing bugs, for maintaining exi...
💡 Top Recommendations:
Andrew Ng says the real bottleneck in AI startups isn't coding — it's product management
- AI sped up coding. Now, the real challenge for startups is product management.
- If a prototype takes a day, waiting a week for user feedback is "really painful," said Andrew Ng.
- The former Google Brain scientist said his teams are "increasingly relying on gut" to make faster decisions.
AI has m...
💡 Top Recommendations:
AI / Tech-Enabled Roll Ups are a Dumb Idea
Once in a while, a new VC investing theme pops up that makes you scratch your head. For the past year, one popular theme / debate has been “tech-enabled rollups”, which is a flavor of the Private Equity rollup strategy but with a twist.
Basically, the idea is that you buy a bunch of “boring” busines...
💡 Top Recommendations:
Here’s Why ‘Cursor for X’ Doesn’t Work in Vertical AI
Here’s Why ‘Cursor for X’ Doesn’t Work in Vertical AI
Coding AI agents had so many things going in their favor.
Recently, it’s become fashionable to use “Cursor for X” as a shorthand for AI agent startups. The phrase evokes memories from 2013 when every other pitch deck was about an “Uber for landsc...
💡 Top Recommendations:
Evals Startups Are Not Enterprise Ready
Evals Startups Are Not Enterprise Ready
They want to be the next "Datadog" or "Snowflake", but can they fool everyone at the same time?
This past week, I was at the AI Engineer conference in SF to get a pulse on the AI propaganda machine. And as expected, the evals hype was in full force—paid keynot...
💡 Top Recommendations:
Using AI Agents to Hunt Prospects 24/7
Using AI Agents to Hunt Prospects 24/7
You are about to interact with AI bots very deep into the funnel...
Most people hate hustling, so why not have AI agents hustle for you?
When people hear “AI for prospecting”, they imagine using AI for drafting outreach emails, enriching leads, or building some...
💡 Top Recommendations:
Sierra's AI Strategy in a Nutshell
Sierra's AI Strategy in a Nutshell
Thoughts on Sierra AI and risk factors for application layer AI startups
A common question in AI circles: where will the value actually accrue—infra or apps? And if it’s apps, which verticals will matter the most?
To answer this question, one startup I monitor clos...
💡 Top Recommendations:
Incumbents Are Starting to Rugpull AI Startups
Incumbents Are Starting to Rugpull AI Startups
Slack just reminded Glean that it's just a ChatGPT wrapper..
Yesterday, TheInformation reported that Slack (owned by Salesforce) effectively “rugpulled”(*) knowledge base startups (e.g. Glean) by severely rate limiting its access to Slack conversations ...
💡 Top Recommendations: