John Paulett

John Paulett

@johnpaulett.com

Engineering Leader & Architect @hoppr.ai #radsky #medsky

223 followers43 following81 posts

John Paulett
@johnpaulett.com

Claude Code + Notion MCP + $DB_Vendor MCP = 🤌 Gave an outline of my idea. Claude took my outline, found the relevant data, and turned it into a polished proposal with hard data in record time.

John Paulett
@johnpaulett.com

My favorite part of Claude Code: I can get an idea out over the weekend. Before: My laptop was a graveyard of personal projects that took all weekend just to get the structure in place. Now with Agentic Coding, I focus on shipping my idea.

John Paulett
@johnpaulett.com

AI Coding tools are evolving quickly -- if you have not tried them in the past month, you owe it to yourself to revisit. I spent the weekend with ChatGPT Codex and Claude Code, and wow 🤯.

View full thread
John Paulett
@johnpaulett.com

3. AI coding is good at those tasks you think take 10 minutes but end up spiraling into multiple hours: e.g., bumping versions and dealing with compatibility issues

John Paulett
@johnpaulett.com

AI Coding tools are evolving quickly -- if you have not tried them in the past month, you owe it to yourself to revisit. I spent the weekend with ChatGPT Codex and Claude Code, and wow 🤯.

View full thread
John Paulett
@johnpaulett.com

A few takeaways: 1. Invest in your CLAUDE.md or AGENTS.md file to give details about the code, what you expect in general, and how to run testing, type checking, and linting. 2. The more type hints and tests you have, the better, as the agent will use these to verify its work

John Paulett
@johnpaulett.com

AI Coding tools are evolving quickly -- if you have not tried them in the past month, you owe it to yourself to revisit. I spent the weekend with ChatGPT Codex and Claude Code, and wow 🤯.

View full thread
John Paulett
@johnpaulett.com

🧠 Claude Code 🧠, which is now included in the $20/mo Pro plan, is like working with a good mid-level developer. Claude took my prompt, implemented multiple subsystems in parallel, and gave me a working prototype. I spent a few more rounds with Claude adding additional functionality.

John Paulett
@johnpaulett.com

In 3-4 hours, I got done what would have taken me 3-4 full days -- most of this work is not rocket science or even the interesting parts of a project (wiring up whatever build system is currently popular, getting all the correct dependency versions).

John Paulett
@johnpaulett.com

AI Coding tools are evolving quickly -- if you have not tried them in the past month, you owe it to yourself to revisit. I spent the weekend with ChatGPT Codex and Claude Code, and wow 🤯.

View full thread
John Paulett
@johnpaulett.com

My Codex team completed 14 Pull Requests: from adding support for newer Python versions, converting to use uv+ruff, to finding a very subtle bug, to correcting longstanding typos.

John Paulett
@johnpaulett.com

I then spent all Sunday morning building a complex prompt describing a prototype. Codex got the basic project structure set, but instead of implementing most functionality, just stubbed it out. A few repeated attempts to build upon that base with smaller parts of my prompt were not getting far.

John Paulett
@johnpaulett.com

AI Coding tools are evolving quickly -- if you have not tried them in the past month, you owe it to yourself to revisit. I spent the weekend with ChatGPT Codex and Claude Code, and wow 🤯.

John Paulett
@johnpaulett.com

🔧 ChatGPT Codex 🔧 runs OpenAI Codex in containers on OpenAI's servers and is now available with ChatGPT Plus ($20/mo). It is like having a team of junior developers. I give them tasks, they do the work, test and type check. I provide some feedback, and they open GitHub Pull Requests.

John Paulett
@johnpaulett.com

How is it 2025 and the receiver of Outlook invites can not control the reminder time 🤯? It's not like we need 15 minutes to walk to a conference room. We're just bouncing between video calls. The number of meetings I forgotten about because I've moved to another task ... @microsoft.com

John Paulett
@johnpaulett.com

Deep dive on NVDA: Despite AI boom, major threats emerge from innovative hardware (Cerebras, Groq), custom silicon (big tech), software alternatives (MLX, Triton), and DeepSeek's 45x efficiency gains. Risks may not be priced in @ 20x sales & 75% margins youtubetranscriptoptimizer.com/blog/05_the_...

youtubetranscriptoptimizer.comThe Short Case for Nvidia StockAll the reasons why Nvidia will have a very hard time living up to the currently lofty expectations of the market.
John Paulett
@johnpaulett.com

🤗 transformers now has ModernBERT included! github.com/huggingface/...

github.comRelease v4.48.0: ModernBERT, Aria, TimmWrapper, ColPali, Falcon3, Bamba, VitPose, DinoV2 w/ Registers, Emu3, Cohere v2, TextNet, DiffLlama, PixtralLarge, Moonshine · huggingface/transformersNew models ModernBERT The ModernBert model was proposed in Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference by B...

John Paulett reposted

Tailscale
@tailscale.com

It's easy to lose sight of the fact that, from a tech perspective, we're absolutely living in the future. Our CEO and co-founder @apenwarr.ca looks at just how powerful our modern machines are — and what that means for all of us

tailscale.comLiving in the future, by the numbersInstead of making the traditional New Year predictions, let’s talk instead about the beautiful technological future we live in: the one that exists right now but we don’t always notice.
John Paulett
@johnpaulett.com

NYC AI > The city’s “AI transformation has begun,” with more than 2,000 AI startups and 40,000 workers already forming a “thriving tech ecosystem,” according to the report by the city’s Economic Development Corporation. gothamist.com/news/ai-will... #nyc #ai #startups

gothamist.comAI will help drive NYC economy in 2025, but some jobs could be 'displaced,' report saysThe city’s artificial intelligence “transformation has begun,” according to the New York City Economic Development Corporation.

John Paulett reposted

Brian Casey
@brian-casey.bsky.social

Start the New Year off right with issue #670 of The Imaging Wire at buff.ly/4gJi0d4: - Is Radiation Dose Too Low? - What Now for Medicare Fix? - What Triggers Radiation Dose Alerts? - RT Enrollment Grows - Mammo Screening Falls Short ... and much more! #radiology #medicalimaging #ImagingAI

buff.lyIs Radiation Dose Too Low? | What Now for Medicare Fix? - The Imaging WireIs radiation dose too low, Medicare fix dies, radiation dose alerts, RT enrollment grows, mammo screening falls short, and much more.
View full thread
John Paulett
@johnpaulett.com

The Masked Language Model task is simple but powerful. Given input like "there is [MASK] consolidation in the right lower lobe," the model would predict that it should be "patchy." The bidirectional nature of encoders means MLM can find speech recognition errors or illogical content.

View full thread
John Paulett
@johnpaulett.com

Part 1 uses the hidden states of the un-tuned ModernBERT body to train a simple Logistic Regression in scikit-learn. In Part 3 we'll do this purely using Hugging Face 🤗 transformers to fine-tune a classifier.

John Paulett
@johnpaulett.com

NLP Classifiers for radiology reports are powerful, few examples: - Extract CPT / ICD codes for billing - Label specific findings or label as normal/abnormal - Detect critical results and follow-up recommendations

John Paulett reposted

Dr Amine Korchi
@draminekorchi.bsky.social

Few years ago, many radiologists thought AI was like mammography CAD—a fleeting fad. But AI isn’t CAD; it’s speech transcription—a tool so essential it will become invisible.

John Paulett
@johnpaulett.com

Great read on 🤗 transformers -- I've been working through the code over the holidays. Amazing to see the advancements in the #NLP world since 2018 and how easy #HuggingFace has made it to use and customize hundreds of models. amzn.to/4guTRXC