The hottest MLOps Substack posts right now

And their main takeaways
Category
Top Technology Topics

Lessons from Building AI Agents for Financial Services

Nicolas Bustamante • 435 implied HN points • 24 Jan 26
🕹 Technology MLOps
  1. Isolated sandboxes and an S3-first, filesystem-backed architecture are essential for safely running multi-step agent workflows and giving each user a private, replayable execution environment.
  2. Clean, normalized context is the product: chunked markdown narratives, structured CSV/tables, and rich JSON metadata are what let agents reliably reason over messy financial sources like SEC filings.
  3. Skills plus the surrounding experience are the moat: lightweight, editable markdown skills, rigorous evals, real-time streaming UX, long-running orchestration, and production monitoring make the product reliable and defensible as models improve.

Deep Learning Weekly: Issue 336

Deep Learning Weekly • 648 implied HN points • 17 Jan 24
🕹 Technology MLOps
  1. This week's deep learning topics include generative AI in enterprises, query pipelines, and closed-loop verifiable code generation.
  2. Updates in MLOps & LLMOps cover CI/CD practices, multi-replica endpoints, and serverless solutions like Pinecone.
  3. Learning insights include generating images from audio, understanding self-attention in LLMs, and fine-tuning models using PyTorch tools.

The Sequence Opinion #786: The Great Absorption: When System Code Becomes Model Weights

TheSequence • 56 implied HN points • 08 Jan 26
🕹 Technology MLOps
  1. Many system and agent capabilities that used to live in external orchestration code are being internalized into model weights, so models now handle tasks once implemented by separate scripts and pipelines.
  2. Hand‑coded scaffolding like prompt chains, vector DB glue, and custom parsers is increasingly at risk of becoming obsolete whenever a new frontier model checkpoint appears, so expect rapid disruption.
  3. Product teams need to distinguish permanent infrastructure from temporary scaffolding and architect systems to tolerate or embrace model internalization, or else large parts of their stack can be replaced overnight.

Deep Learning Weekly: Issue 335

Deep Learning Weekly • 393 implied HN points • 10 Jan 24
🕹 Technology MLOps
  1. AI models are assisting robots to execute complex tasks more transparently using multiple foundation models.
  2. LLMs are being used to solve reasoning problems and enhance tool use in deep learning.
  3. AutoRT is a system proposing diverse instructions to robots, leveraging VLMs and LLMs to scale up operational robot deployment.

The Broken Leg Check

Abstraction • 34 implied HN points • 07 Jan 26
🕹 Technology MLOps
  1. Do a quick "broken leg" check first because a decisive news event can resolve a question immediately and save the time and cost of running the full forecasting pipeline.
  2. Be cautious: a wrongly triggered broken-leg update is dangerous since proper scoring heavily penalizes confident incorrect forecasts, so false positives can wipe out gains.
  3. Treat it as an empirical trade-off: implement a news-based detector, clearly define what "overwhelmingly resolves" means, track when it fires, and tune thresholds, confidence damping, or disable it if blowouts outweigh the savings.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

SwirlAI Table of Contents

SwirlAI Newsletter • 432 implied HN points • 28 Jun 23
🕹 Technology MLOps
  1. The newsletter provides a Table of Contents with more than 90 topics, making it easier to find the content of interest.
  2. Topics covered include Data Engineering fundamentals, Spark architecture, Kafka use cases, MLOps deployment processes, System Design examples, and more.
  3. If interested, it's recommended to support the author's work by subscribing and sharing the content.

MLOps Basics - For Data Engineers.

Data Engineering Central • 393 implied HN points • 15 May 23
🕹 Technology MLOps
  1. Working on Machine Learning as a Data Engineer is not as hard as it seems - it falls somewhere in the middle of difficulty.
  2. Machine Learning work for Data Engineers focuses on MLOps like feature stores, model prediction, automation, and metadata storage.
  3. The key aspects of MLOps include automating tasks, using tools like Apache Airflow, and managing metadata for a stable ML environment.

SAI #22: Decomposing the Data System.

SwirlAI Newsletter • 294 implied HN points • 18 Mar 23
🕹 Technology MLOps
  1. Learning to decompose a data system is crucial for better reasoning and understanding of large infrastructure
  2. Decomposing a data system allows for scalability, identification of bottlenecks, and total event processing latency optimization
  3. The different layers in a data system include data ingestion, transformation, and serving layers, each with specific functions and technologies

Deep Learning Weekly: Issue 339

Deep Learning Weekly • 137 implied HN points • 07 Feb 24
🕹 Technology MLOps
  1. Google introduced a new model for time-series forecasting called TimesFM, pre-trained on a large time-series corpus.
  2. Adept introduced a new multimodal model called Adept Fuyu-Heavy designed for digital agents.
  3. There are various articles and papers covering topics like LLM platforms, code implementation like LoRA, and new generation AI models.

Deep Learning Weekly: Issue #319

Deep Learning Weekly • 275 implied HN points • 20 Sep 23
🕹 Technology MLOps
  1. Google's Bard Extension now scans Gmail, Docs, and Drive for answers with its AI chatbot.
  2. Optimizing LLMs from a dataset perspective involves strategies for finetuning using existing datasets.
  3. Influence Functions offer insights into large language model generalization, improving accuracy and robustness through dataset reinforcement.

Deep Learning Weekly : Issue #297

Deep Learning Weekly • 275 implied HN points • 19 Apr 23
🕹 Technology MLOps
  1. Meta open-sources DINOv2 for computer vision models with self-supervised learning.
  2. European lawmakers call for tighter controls on powerful general-purpose AI.
  3. Various articles explore topics like building LLM applications, understanding parameter-efficient fine-tuning, and consistency models.

SAI #19: The Data Value Chain.

SwirlAI Newsletter • 255 implied HN points • 25 Feb 23
🕹 Technology MLOps
  1. Understanding the Data Value Chain is essential for building successful Data Products.
  2. Implementing Data Contracts in the Data Pipeline ensures data quality and prevents unexpected outages.
  3. Knowing the 4 types of ML Model Deployment helps in deploying machine learning models effectively.

Deep Learning Weekly : Issue #324

Deep Learning Weekly • 235 implied HN points • 27 Oct 23
🕹 Technology MLOps
  1. This post covers updates in deep learning including new AI models and techniques.
  2. Industry highlights include open-sourcing Fuyu-8B, AI in robotic learning, and funding for AI startups.
  3. Topics on MLOps, LLMOps, learning, and libraries provide insights on various aspects of AI development.

Deep Learning Weekly: Issue #308

Deep Learning Weekly • 255 implied HN points • 05 Jul 23
🕹 Technology MLOps
  1. This week's issue of Deep Learning Weekly covers Meta's AI system cards, real-time machine learning foundations at Lyft, and a local code generator tool using Microsoft's guidance library.
  2. Industry news includes Inflection AI's $1.3B investment, Meta AI sharing 22 system cards on AI experiences, and Unity launching new AI platforms for real-time 3D creation.
  3. In the MLOps and Learning sections, topics range from dealing with train-serve skew in ML models to using LLMs for data extraction and building local code generators.

Deep Learning Weekly: Issue 337

Deep Learning Weekly • 117 implied HN points • 24 Jan 24
🕹 Technology MLOps
  1. DeepMind introduces AlphaGeometry, an AI system solving complex geometry problems at Olympiad level.
  2. ElevenLabs, an AI voice startup, raises $80 million in funding, reaching a valuation of $1.1 billion.
  3. Theory suggests that large language models like LLMs are more than just 'stochastic parrots.'

Deep Learning Weekly: Issue #293

Deep Learning Weekly • 216 implied HN points • 22 Mar 23
🕹 Technology MLOps
  1. This week in deep learning includes Microsoft 365 Copilot and emergent abilities of large language models.
  2. Learn about industry trends like signed parameters for ML model deployments and new AI startups.
  3. Explore informative posts on prompt engineering, computer vision in robotics, and papers on video generation and symbolic regression.

Deep Learning Weekly : Issue #309

Deep Learning Weekly • 216 implied HN points • 12 Jul 23
🕹 Technology MLOps
  1. Deep Learning Weekly Issue #309 covers topics like Code Interpreter on ChatGPT Plus and ML system design with 200 case studies.
  2. Industry innovations include AI-generated chart captions and Nvidia's AI approach to carbon capture.
  3. Learning section highlights topics like Tiny Audio Diffusion and Swin Transformer for object recognition.

Deep Learning Weekly: Issue #317

Deep Learning Weekly • 216 implied HN points • 07 Sep 23
🕹 Technology MLOps
  1. Google introduced WeatherBench 2 for the next generation of weather models.
  2. OpenAI provided a guide for teachers on using ChatGPT in classrooms.
  3. A paper discussed Prompt2Model, a method to generate deployable models from natural language instructions.

The AI user's guide to evals

Technically • 14 implied HN points • 11 Dec 25
🕹 Technology MLOps
  1. Evals are software tests for AI that turn fuzzy model outputs into measurable metrics so you can find and fix errors instead of guessing.
  2. Look at your data first — analyze real outputs to spot where the model fails, because you can’t measure or fix problems you don’t identify.
  3. Start with simple keyword checks and assertions before building complex “LLM-as-judge” setups, and iterate: test, fix, measure, repeat; otherwise your system just feels like a slot machine.