Sign in

Nathan Clement

@njclement.com
259 followers 999 following 121 posts

Fintech Staff Engineer. AI & Philosophy. Follower of Christ. Be 100% of who you ought to be!

PostsRepliesMedia
Nathan Clement @njclement.com · 07/10/2026
My wife quit her job as a Medical Assistant to become a software developer, and just published her first article :) njclement.com/writing/good...
njclement.com
Good Vibes: My Journey Into AI and Vibe Coding
How 14 years in healthcare led to vibe coding, software engineering, and a new way of helping people through AI and technology.
000
Nathan Clement @njclement.com · 26/09/2026
Quick anonymous poll: how are you actually encountering AI these days? Using it daily, hate it passionately, watching it float by on social, somewhere in between? Seven questions, under a minute, no email collected. Would love responses and shares. docs.google.com/forms/d/e/1F...
docs.google.com
AI Opinions Poll
A short, anonymous poll about how people feel about and use AI. No names, email addresses, or other personal information are collected, and every question is optional.
001
Nathan Clement @njclement.com · 23/08/2026
Seems like it has been getting harder and harder to get out into nature in Oregon. Last paddle-board trip we had to get three permits and pay for parking at two places. Thanks Washington for keeping it easy to get outside! Lacamas Lake was beautiful 🤙
000
Nathan Clement @njclement.com · 21/08/2026
Look. Us regular folk will never be able to raise a clone army in time to fight off the Silicon Valley droid army unless we have super powerful AI to help us figure out how to accelerate the growth process.
000
Nathan Clement @njclement.com · 20/08/2026
PDX needs to put an MLB Stadium at Gateway. None of this downtown on the waterfront with no parking and blocking hospital access silliness.
000
Nathan Clement @njclement.com · 13/10/2025
My wife left medical to become a vibe coder. Once in a while I review her code, and am regularly in awe of her velocity and work quality. Her secret? She knows exactly what she wants, has incredible attention to detail, and asks her AI assistant to explain its choices.
030
Nathan Clement @njclement.com · 05/08/2025
Everyone’s watching the AI breakthroughs. The actual war? It’s the silent backroom talent deals, culture curation, contracts, counteroffers, people sliding between teams, while everyone else argues about code.
010
Nathan Clement @njclement.com · 05/08/2025
Trying to supercharge Claude agent workflows. Manual "@" calls are a pain, making real orchestration feel out of reach. Has anyone cracked agent delegation, maybe with clever hooks? Craving thoughts from folks in the trenches. Share for visibility if you feel the same way!
020
Nathan Clement @njclement.com · 27/06/2025
Humans write far sloppier #slop than #LLMs could even dream of generating ✍️
010
Nathan Clement @njclement.com · 24/05/2025
You can just ask for things... How will GenAI change data pipeline engineering? #tech #developer #software #data #ai
030
Nathan Clement @njclement.com · 12/05/2025
Freeway was flooded on my way to imaging appointment today at OHSU! #pdx
000
Nathan Clement @njclement.com · 25/04/2025
The video is too long for Bluesky, but if you're worried about AI making Engineers dumber, check this out!
linkedin.com
Worried about Cursor and Windsurf rotting your brain? In this video I… | Nathan Clement
Worried about Cursor and Windsurf rotting your brain? In this video I discuss why I believe AI will have a different effect on the cognitive ability of engineers, depending on how they approach AI dr...
130
Nathan Clement @njclement.com · 22/04/2025
The next wave of great software engineers will be philosophers and lawyers
000
Nathan Clement @njclement.com · 28/03/2025
Do LLMs think in a language of their own? Do LLMs plan ahead beyond the next token? Why do models hallucinate? Incredible research by Anthropic just dropped: www.anthropic.com/research/tra...
anthropic.com
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
020
Nathan Clement @njclement.com · 26/03/2025
It just works
The Omni Models are OpenAI's play at becoming the "Apple" of AI
000
Nathan Clement @njclement.com · 25/03/2025
Starting April 1, Visa is deprecating old Fraud/Dispute management systems in favor of a new, enhanced program called VAMP > Strong incentives for pre-auth prevention > Changes to fee structure > New tools/resources Details below: merchantfraudjournal.com/visa-acquire... What do people think?
merchantfraudjournal.com
Visa Acquirer Monitoring Program (VAMP) Changes 2024: New Rules and Compliance Tips
As part of Visa’s ongoing efforts to streamline and enhance its monitoring programs, effective as of March 31, 2025, Visa
000
Nathan Clement @njclement.com · 25/03/2025
Use case for LLM Agents: TDD for Integration Docs. > Step 1: Create fresh application > Step 2: Point Agent at Docs (maybe an llms.txt?) > Step 3: Ask Agent to integrate with your product ✅ Pass = Integration works Automating this process would be a cool product!
020
Nathan Clement @njclement.com · 06/03/2025
Last week I had a "Black Mirror" thought about a potential negative AI future, so I wrote a short story about it. Curious what folks think :) #shortstory articles.njclement.com/we-chose-the...
articles.njclement.com
010
Nathan Clement @njclement.com · 04/03/2025
Testing out our latest integration with the National Do Not Call Registry 📵 AI summary looking nice as well!
An AI Summary of a checkpoint workflow in Dodgeball showing that a phone number used in this test workflow had 110 reported violations reported to the National Do Not Call Registry
010
Nathan Clement @njclement.com · 17/02/2025
When you just built your first AI model and ask your senior why it won’t generalize…
010
Nathan Clement @njclement.com · 05/02/2025
AI does not make simple mistakes, it makes complex ones.
110
Nathan Clement @njclement.com · 04/02/2025
Keeping these pillars strong isn’t just a technical challenge: it’s a strategic imperative for protecting both your users and your bottom line. Read the full article for explanations and stories! dodgeball-engineering.medium.com/4-critical-f...
dodgeball-engineering.medium.com
4 Critical Features When Engineering Your Own Anti-Fraud System
Building an anti-fraud system is like constructing a fortress: it must be carefully designed to withstand both external attacks and…
110
Nathan Clement @njclement.com · 31/01/2025
How can you protect a Shopify store from fraud using the Dodgeball App?? Video breakdown 0:00 Introduction 0:31 The Checkpoint Editor 0:42 A Simple Test for Emails 1:45 Email Analysis with AtData 2:52 Test Order on Shopify 3:18 Payment Protection with Sift 4:48 More Capabilities 5:27 Summary
youtu.be
Protecting your Shopify Store with Dodgeball
YouTube video by Dodgeball
041
Nathan Clement @njclement.com · 31/01/2025
Someone should build an app called Mt. Olympus, where top models debate as agents until they reach a mutually agreed solution to complex queries, and you can watch the "distributed" chain of thought live. Too many ideas and too little time to do it myself :P
000
Nathan Clement @njclement.com · 28/01/2025
What should we take away from the DeepSeek drama over the last weekend? 1. Complacency loses 2. Historical success is not a guarantee of future outcomes 3. Rearguard actions (like limiting access to NVIDIA GPUs) are not solution Innovate, don't entrench.
020
Nathan Clement @njclement.com · 24/01/2025
I listen to audiobooks every morning. I get physical copies of my favorites. One of these favorites is “Extreme Ownership” by Jocko Willink and Leif Babin This pictured section below struck me today. “Simple”
100
Nathan Clement @njclement.com · 23/01/2025
Curious about using Dodgeball from an Engineering Perspective? Check out our first video tutorial, designed to show engineers everything they might need to know about working with Dodgeball! #software #engineer #dev #fraud #fraudfighter
youtu.be
Zero to Hero: Everything Engineers need to know about Configuring Dodgeball (Next.js Edition)
YouTube video by Dodgeball Engineering
000
Nathan Clement @njclement.com · 15/01/2025
One example of a value-added use of LLMs: At @dodgeball-eng.bsky.social - we are crafting Agentic AI Workflows to augment and normalize information, providing predictable inputs for decisions: 🧵(1/3)
120
Reposted by Nathan Clement
Andrew@Dodgeball 🍁 @andrew-at-sea.bsky.social · 07/01/2025
It's always a good day when one of your customers is willing to talk about using your software to save money: www.linkedin.com/posts/mercha...
linkedin.com
MRC | Merchant Risk Council on LinkedIn: #paymentsoptimization
In a rapidly growing subscription business, maintaining a proactive fraud posture is critical to optimizing both cost and effectiveness. Building a scalable…
011
Nathan Clement @njclement.com · 13/01/2025
How do engineers stay relevant in an #ai driven future? Get good at knowing what to build, and describing it in elegant, technical detail
120
Nathan Clement @njclement.com · 08/01/2025
The inaugural article by the Dodgeball Engineering Team is now live! Uncovering Engineering Best Practices for Fraud Better Protection with Less Work Let us know what you think of our lessons learned 🔬 dodgeball-engineering.medium.com/uncovering-e...
dodgeball-engineering.medium.com
Uncovering Engineering Best Practices for Fraud
Better Protection with Less Work
010
Nathan Clement @njclement.com · 08/01/2025
Really excited about an article in the pipeline explaining how to think about fraud in 2025 as an Engineer. Here's a little taste!
A simple black-and-white graphic with the heading “Should you bother fighting fraud?” in large bold text. Below it, in smaller text, reads: “Stop guessing! Compute the net value of your anti-fraud strategy today:”

Underneath is an equation that says:
	•	Net Value = Value ( (Prevented Fraud) + (BrandTrust) – (Friction) ) – Cost( (Protection) + (BrandDmg) )

Where:
	•	“Prevented Fraud” is labeled “Fraud Prevented,”
	•	“BrandTrust” is labeled “Perceived Trustworthiness,”
	•	“Friction” is labeled “Lost Business,”
	•	“Protection” is labeled “People, Hardware, Software,”
	•	“BrandDmg” is labeled “False Positives.”
062
Nathan Clement @njclement.com · 07/01/2025
Wanting useful things is the new superpower
010
Nathan Clement @njclement.com · 04/01/2025
v0 by @vercel.com could become the only mockup tool engineers need.
131
Nathan Clement @njclement.com · 01/01/2025
Easing back into the year with some food engineering 🤣 Our first homemade sourdough and butter turned into some mighty nice breakfast! Credit to @OpenAI for the sourdough recipe and my wife’s Italian heritage for knowing what to do with it🧑‍🍳
000
Nathan Clement @njclement.com · 31/12/2024
Exercise is part of your job as an engineer 🧵 (1/3)
100
Nathan Clement @njclement.com · 29/12/2024
This weekend, my wife and I took our little Ford Ranger through the Mt. Baker-Snoqualmie National Forest. The lack of cell signal and new vistas helped kick off my contemplative side, adding structure to the vision for Dodgeball in 2025.
A clipboard full of notes viewed from the road
110
Nathan Clement @njclement.com · 23/12/2024
Working with ML in Python, but aren't sure how to set useful hyper-parameters? Optimize your approach with Grid Search and Cross Validation! Example below used to train a supervised classifier... ⚡️Parallelize with n_jobs=-1
010
Nathan Clement @njclement.com · 19/12/2024
Using pandas read_sql_query() with the chunksize parameter and a streamable SQLAlchemy connection lets you handle arbitrarily large tables efficiently. Great for querying large tables, performing ETL operations, and streaming results to S3 as CSVs for downstream processing.
000
Nathan Clement @njclement.com · 11/12/2024
Ellie wants everyone to know that she has no idea how this happened, she just found the tissue like this 🤣 #personal
Ellie the dog making a very guilty face behind a torn up tissue
000
Nathan Clement @njclement.com · 11/12/2024
Spent the day writing TONS of internal documentation for our customer success team for a big training tomorrow. Not sure how to feel about it to be honest! At least it is top tier LLM embedding fodder🤖🍔 Maybe I should use it to generate updates for customer facing docs?
010
Nathan Clement @njclement.com · 09/12/2024
Big #o1 gap #openai - it can tell me all sorts of things about the theoretical aspects of music, but cannot identify even simple tunes. The song here is "Fly me to the moon" even if you only play the melody on the second line it takes no time to recognize. Anyone want to try #o1-pro on this?
010
Nathan Clement @njclement.com · 03/12/2024
If you're interested in trying out @dodgeballhq.bsky.social and have a Shopify store, you can be up and running without ever needing to talk to an Engineer! It was a total pleasure to build on Shopify.
apps.shopify.com
Dodgeball - Dodgeball - Stop Fraud in its Tracks | Shopify App Store
Easily integrate Dodgeball with your online store, no engineering required. Start building out your anti-fraud policies today using our Checkpoint Studio.
031
Reposted by Nathan Clement
Mateusz Burzyński @andarist.bsky.social · 29/11/2024
Inspired by @tkdodo.eu, I opened a PR with a codefix proposal to add "missing" awaits into return statements in async function enclosed by try statements github.com/microsoft/Ty...
github.com
Implement codefix for adding missing `await` in `return` statements enclosed by try statements by Andarist · Pull Request #60642 · microsoft/TypeScript
Given that async functions flatten returned promises it's a fairly easy mistake to make to assume that try/catch/finally enclosing a returned promise can handle that as if return await p would ...
5314
Nathan Clement @njclement.com · 28/11/2024
Wasn’t expecting to be talking about RAG pipelines today 😂 #thanksgivingdinnerconversation
000
Nathan Clement @njclement.com · 27/11/2024
What is the best Domain Management Service out there these days? Not sure I want to stick with Squarespace after Google domains migration… #buildinpublic folks have any thoughts?
220
Nathan Clement @njclement.com · 26/11/2024
PSA: It's easy to change your 🦋 handle to your own domain, even if you've already started with a .bsky.social handle Check "Settings/Account/Handle" and use the form below to get values to enter into your DNS. They also provide an option to upload a well-known file!
Screenshot of Bluesky Change Handle Form
000
Nathan Clement @njclement.com · 25/11/2024
Problem: I want to create a type-safe dictionary with all combinations of two enums as keys. Solution: Use Template Literal Types to programmatically define a union of valid keys: Result: No invalid keys allowed, fully type-checked! 💪 #TypeScript #Dev
050
Nathan Clement @njclement.com · 25/11/2024
2012 classic from the Harvard i-lab about disrupting via data. Highlights: 🙈 Unscientific approaches with data are worse than random chance. 💎 Higher charges made customers more willing to disrupt their practices, and thus realize value 🫶 Best early hire focused on customer experience and support.
youtube.com
Harvard i-lab | Building a Startup around Disruptive Data with Scott Friend
YouTube video by Harvard Innovation Labs
000