HN user

htahir111

70 karma
Posts30
Comments18
View on HN
skillburst.ai 14d ago

Show HN: Skillburst - AI skills for your whole team, not just the engineers

htahir111
2pts0
skillburst.ai 15d ago

Show HN: Git-Backed Skill Sharing for Non Techies

htahir111
1pts0
github.com 16d ago

Show HN: Record, replay, and improve AI agents in production

htahir111
2pts0
agents-vs-workflows.streamlit.app 1y ago

Agent or Workflow? (Interactive Quiz)

htahir111
3pts1
www.zenml.io 1y ago

Performance Improvement Through SQLAlchemy and FastAPI Optimizations

htahir111
2pts0
www.zenml.io 1y ago

AI Engineering vs. ML Engineering: Evolving Roles in the GenAI Era

htahir111
2pts1
github.com 2y ago

Upgrading to Pydantic v2 – 433 commits later

htahir111
3pts0
github.com 2y ago

Show HN: ML pipeline that creates a model to produce ML pipelines

htahir111
4pts2
docs.zenml.io 2y ago

A MLOps Starter Guide

htahir111
2pts1
www.zenml.io 2y ago

Hugging Face to Sagemaker Endpoints with MLOps Pipelines

htahir111
1pts0
mlstacks.zenml.io 2y ago

Show HN: Python Package to spin up MLOps infrastructure with Terraform

htahir111
4pts0
github.com 2y ago

Show HN: MLStacks – open-source tool to deploy MLOps infrastructure in minutes

htahir111
3pts0
sandbox.zenml.io 3y ago

Show HN: One-Click MLOps Platform Sandbox with ZenML, MLflow, Kubeflow and MinIO

htahir111
6pts0
www.you-tldr.com 3y ago

Show HN: You-tldr-Summarize and Interact with YouTube Videos in your language

htahir111
4pts2
www.gittrends.xyz 3y ago

Show HN: GitTrends – Find out when you're trending on GitHub

htahir111
5pts5
github.com 4y ago

Open Source Data Annotation and Labeling Tools

htahir111
3pts0
zenml.substack.com 4y ago

The Anti-Stealth Startup

htahir111
11pts1
hackernoon.com 5y ago

Develop ML in Pipelines

htahir111
1pts0
htahir1.medium.com 5y ago

ML should be written as pipelines from the get-go

htahir111
2pts0
zenml.io 5y ago

Show HN: Production ready ML from day 0

htahir111
4pts0
github.com 5y ago

Show HN: Machine Learning Pipelines with Integrations

htahir111
2pts0
hackernoon.com 5y ago

ML in Production Is Broken

htahir111
3pts0
github.com 5y ago

Show HN: Deploy ML Models on a Budget

htahir111
117pts47
github.com 5y ago

Show HN: BudgetML – Deploy your ML model in 10 lines of code while saving 80%

htahir111
4pts0
blog.maiot.io 5y ago

Machine learning faces a reproducibility crisis

htahir111
3pts0
blog.maiot.io 5y ago

Is your machine learning reproducible?

htahir111
4pts0
maiot.io 5y ago

Show HN: Automate ML with Repeatable Pipelines

htahir111
2pts0
blog.maiot.io 6y ago

Splitting your dataset in ML is an underappreciated art

htahir111
3pts0
blog.maiot.io 6y ago

Avoiding technical debt in ML development: A practical guide

htahir111
4pts0
blog.maiot.io 6y ago

Show HN: Deep Learning 33M data points using a few lines of YAML

htahir111
7pts0

I recently gave a talk arguing that most companies don't actually need AI "agents" - they need workflows. The agent/workflow distinction has become one of the most confusing topics in AI engineering, since the "Building Effective Agents" blog from Anthropic: https://www.anthropic.com/engineering/building-effective-age....

My definition: An agent is a system where the LLM controls its own execution flow based on environmental feedback. Everything else (prompt chaining, routing, parallelization, orchestrator-worker) is a workflow, even if it uses LLMs.

The problem is the line is incredibly blurry. To illustrate this, I built an interactive quiz with 7 code examples that test your intuition on what's an agent vs workflow.

The community voting results are fascinating - even technical folks disagree on edge cases like "research agents" with only 3 predefined action types, or orchestrator-worker patterns where the LLM dynamically determines task structure.

The quiz shows live voting results, so you can see how your intuitions compare to others. Would love to hear HN's take - where do you draw the line?

Recently wrote a step-by-step guide using the open-source ZenML (Disclaimer: I'm the co-creator). Thought it covered some nice concepts and is OSS, so the HN community would appreciate. Peace!

Airflow's Problem 4 years ago

Wouldn't it make sense to decouple the orchestration later from the authoring layer for the dags? That way you could solve the authoring problems separately from the lower level orchestration problems. We're trying this over at ZenML (https://zenml.io) but have yet to get feedback

ZenML is hiring for a Design Engineer | Remote-friendly | Freelancer or Employee | Full-time or Part-time

ZenML is an extensible, open-source MLOps framework to create production-ready machine learning pipelines. Built for data scientists, it has a simple, flexible syntax, is cloud- and tool-agnostic, and has interfaces/abstractions that are catered towards ML workflows.

We’re looking for a Design Engineer with a multi-disciplinary skill-set who can take over the look and feel of the ZenML experience. ZenML is a tool designed for developers and we want to delight them from the moment they land on our web page, to after they start using it on their machines. We would like a consistent design experience across our many touchpoints (including the [landing page](https://zenml.io), the [docs](https://docs.zenml.io), the [blog](https://blog.zenml.io), the [podcast](https://podcast.zenml.io), our social media, the product itself which is a [python package](https://github.com/zenml-io/zenml) etc).

A lot of this job is about communicating complex ideas in a beautiful way. You could be a developer or a non-coding designer, full time or part-time, employee or freelance. We are not so picky about the exact nature of this role. If you feel like you are a visually creative designer, and are willing to get stuck in the details of technical topics like MLOps, we can’t wait to work with you!

Apply here: https://zenml.notion.site/Design-Engineer-m-f-1d1a219f18a341...

Yes this is aimed at being a simpler API rather than complicated one. Also MLFlow does not orchestrate self-starting preemptible instances, so you'd have to pay the full amounts.

OP here. Probably some form of container orchestration system like Kubernetes to manage the deployments + resources. There is also specialized ML tooling like Kubeflow to help out. Its still a developing landscape though.

We made BudgetML not to replace the above but to make it easy for scenarios where the need would be to just "get out there and deploy". Do you see value in that too?