CodewithP's profile picture. 🙋‍♂️ SWE @ServiceNow 
👨‍💻 Talks to software & cats 🐈  
QE's are not my best friends 👀

codewithP

@CodewithP

🙋‍♂️ SWE @ServiceNow 👨‍💻 Talks to software & cats 🐈 QE's are not my best friends 👀

고정된 트윗

Building cool shit with AI and posting about it ✍️ Currently: 🤖 Going all out on Model Context Protocol 🤓 Diving into Deep Learning & research & sharing fundamental insights 🚢 Creator of MCP Maker & Adam Ascension (game) 📑 Published research paper on Recommendation Systems…


what's stopping you from coding like this?

Rate my setup

Manixh02's tweet image. Rate my setup


it'll be ideal if @GeminiApp were to show progress of a task to know how long we need to wait, like @ChatGPTapp does. It's been 8 minutes already!!!

CodewithP's tweet image. it'll be ideal if @GeminiApp were to show progress of a task to know how long we need to wait, 
like @ChatGPTapp  does.
It's been 8 minutes already!!!
CodewithP's tweet image. it'll be ideal if @GeminiApp were to show progress of a task to know how long we need to wait, 
like @ChatGPTapp  does.
It's been 8 minutes already!!!

codewithP 님이 재게시함

LLM as a judge has become a dominant way to evaluate how good a model is at solving a task, since it works without a test set and handles cases where answers are not unique. But despite how widely this is used, almost all reported results are highly biased. Excited to share our…

Kangwook_Lee's tweet image. LLM as a judge has become a dominant way to evaluate how good a model is at solving a task, since it works without a test set and handles cases where answers are not unique.

But despite how widely this is used, almost all reported results are highly biased.

Excited to share our…
Kangwook_Lee's tweet image. LLM as a judge has become a dominant way to evaluate how good a model is at solving a task, since it works without a test set and handles cases where answers are not unique.

But despite how widely this is used, almost all reported results are highly biased.

Excited to share our…
Kangwook_Lee's tweet image. LLM as a judge has become a dominant way to evaluate how good a model is at solving a task, since it works without a test set and handles cases where answers are not unique.

But despite how widely this is used, almost all reported results are highly biased.

Excited to share our…

codewithP 님이 재게시함

AI/ML Engineers don’t skip this! This Stanford University course is a true gold mine covering everything you need to build and fine-tune LLMs from the ground up

VTikke's tweet image. AI/ML Engineers  don’t skip this!
This Stanford University course is a true gold mine covering everything you need to build and fine-tune LLMs from the ground up

codewithP 님이 재게시함

Attention: Google has dropped a new version of Attention Is All You Need!

Yuchenj_UW's tweet image. Attention:

Google has dropped a new version of Attention Is All You Need!

codewithP 님이 재게시함

A reminder

venturetwins's tweet image. A reminder

codewithP 님이 재게시함

Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better. I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was…

AndrewYNg's tweet image. Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better.

I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was…

It’s here :) Go crazy kids👨‍💻

Introducing Claude Opus 4.5: the best model in the world for coding, agents, and computer use. Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.

claudeai's tweet image. Introducing Claude Opus 4.5: the best model in the world for coding, agents, and computer use.

Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.


Bro disappeared like it never existed

CodewithP's tweet image. Bro disappeared like it never existed

codewithP 님이 재게시함

The source code of Windows troubleshooting program has leaked

codewithpri's tweet image. The source code of Windows troubleshooting program has leaked

Its gonna be a good day :) #perplexity_ai

CodewithP's tweet image. Its gonna be a good day :)

#perplexity_ai

codewithP 님이 재게시함

Before Chrome 😂

lingodotdev's tweet image. Before Chrome 😂

Ngl, Its been good Some things are breaking Like Ice (from Jordan Baird) & the battery toolkit app. But nothing like a deal breaker. Aesthetics are cool.

CodewithP's tweet image. Ngl, Its been good

Some things are breaking 
Like Ice (from Jordan Baird) & the battery toolkit app.

But nothing like a deal breaker.
Aesthetics are cool.

Alright then. Let’s see what’s all that fuss about #macOS #Tahoe

CodewithP's tweet image. Alright then.
Let’s see what’s all that fuss about

#macOS #Tahoe


No Never Even if there is We’re with @getpostman

is there any API testing tool better than postman?

_devJNS's tweet image. is there any API testing tool better than postman?


codewithP 님이 재게시함

I created this Cricket game using Gemini 3 and it's too good. Vibe coding is gonna be fun now.


Why the heck do tech companies sponsor f1 races?? 🥴


Alright then. Let’s see what’s all that fuss about #macOS #Tahoe

CodewithP's tweet image. Alright then.
Let’s see what’s all that fuss about

#macOS #Tahoe

Did you know 👀 ServiceNow is one of Fortune’s World’s Best Workplaces for the third year in a row! Grateful to be part of a group of incredible people who make our culture so special. See what makes our workplace one of the world’s best: spr.ly/60167giUa


Done with the “Structuring ML Projects” @coursera 🤖📚 (just revising already studied concepts 🙃) Key learnings: • error analysis isn’t optional, it’s the map • bias vs variance → stop guessing • data distribution problems are the real villains • transfer learning = cheat…

CodewithP's tweet image. Done with the “Structuring ML Projects” @coursera  🤖📚 (just revising already studied concepts 🙃)

Key learnings:
• error analysis isn’t optional, it’s the map
• bias vs variance → stop guessing
• data distribution problems are the real villains
• transfer learning = cheat…

Loading...

Something went wrong.


Something went wrong.