Prashant Mudgal

1.9K posts

Prashant Mudgal banner
Prashant Mudgal

Prashant Mudgal

@prashantmdgl9

A human being

New York Katılım Şubat 2011
230 Takip Edilen113 Takipçiler
Prashant Mudgal retweetledi
Dhairya
Dhairya@dkare1009·
Google just dropped a FREE AI Agents course. And almost no one is talking about it. 10+ code samples, whitepapers, hands-on projects... all in one place. Here’s the full breakdown (5 days): Day 1: Foundations of AI Agents Learn how agents actually work: • Architecture • Capabilities • How they differ from LLMs → Build systems that can perceive, plan, act Whitepaper: lnkd.in/grYivvCW Code: lnkd.in/gcDruAx7 Day 2: Tools & MCP (Model Context Protocol) Agents don’t work alone. Learn: • Tool usage & APIs • MCP architecture • Human-in-the-loop workflows Whitepaper: lnkd.in/gnU9yqqW Code: lnkd.in/g5ZQHGzg Day 3: Context Engineering (Memory) This is where agents become powerful. • Sessions → short-term memory • Persistent memory → long-term learning Whitepaper: lnkd.in/g9WztfuP Code: lnkd.in/g4mQEtPE Day 4: Agent Quality Production-ready systems need reliability. Learn: • Logs, traces, metrics • Evaluation frameworks • LLM-as-a-judge Whitepaper: lnkd.in/g-SAMSpV Code: lnkd.in/gJxMN46g Day 5: From Prototype → Production Where most people fail. • Deployment strategies • Scaling agents • Agent-to-Agent communication • Vertex AI ecosystem Whitepaper: lnkd.in/gnUAscjM Code: lnkd.in/gnikixYA This is basically a complete roadmap to building AI agents in 2026. And it’s 100% free. Save this. You’ll need it later 💾 Like 👍 • Repost ♻️ Follow for no-BS AI insights 🚀
Dhairya tweet media
English
15
286
1.3K
99.5K
Prashant Mudgal retweetledi
Ruben Hassid
Ruben Hassid@rubenhassid·
Prompting is the worst way to use Claude. Here's what the top 1% do instead: 1. Open the Claude desktop app. 2. Click "Cowork" (not Chat). 2. Point it to a folder with your context files. 3. Create 3 files: about-me, my-voice, my-rules. 4. Use this setup guide: claude-co.work Claude now reads your brain. Every session. But here's where it gets powerful: Before you prompt, change these 2 settings: 1. Turn on "Extended Thinking" It forces Claude to think before answering. 2. Select "Opus 4.6" model. It is the best model for deep, multi-step work. Then stop writing prompts. Paste this instead: "I want to [TASK]. Read all files first. Ask me questions using AskUserQuestion before you execute. Do not guess." Claude generates clickable buttons. It executes. The secret was never the prompt. It was the setup. But to go even deeper, use my full playbook: claude-co.work
Ruben Hassid tweet media
Ruben Hassid@rubenhassid

x.com/i/article/2029…

English
57
349
2.6K
449.6K
Prashant Mudgal retweetledi
Andrej Karpathy
Andrej Karpathy@karpathy·
Thank you Sarah, my pleasure to come on the pod! And happy to do some more Q&A in the replies.
sarah guo@saranormous

Caught up with @karpathy for a new @NoPriorsPod: on the phase shift in engineering, AI psychosis, claws, AutoResearch, the opportunity for a SETI-at-Home like movement in AI, the model landscape, and second order effects 02:55 - What Capability Limits Remain? 06:15 - What Mastery of Coding Agents Looks Like 11:16 - Second Order Effects of Coding Agents 15:51 - Why AutoResearch 22:45 - Relevant Skills in the AI Era 28:25 - Model Speciation 32:30 - Collaboration Surfaces for Humans and AI 37:28 - Analysis of Jobs Market Data 48:25 - Open vs. Closed Source Models 53:51 - Autonomous Robotics and Atoms 1:00:59 - MicroGPT and Agentic Education 1:05:40 - End Thoughts

English
315
388
5.4K
1M
Prashant Mudgal retweetledi
Deedy
Deedy@deedydas·
Karpathy says "I haven't typed a line of code since December" in his latest podcast. Here are the 10 most interesting things he said: Industry-level thoughts: 1. The new way to code is the Peter Steinberg (OpenClaw) way. Have 10 Claude Code / Codex windows open in parallel. The skill is now more how to manage a small org of agents. You need to know how to carve up a codebase into parallel non-conflicting workstreams, write good specs so agents don't go off the rails, and tune when you should review code output. 2. Open source started 18mos behind frontier and is now 6-8mos behind. He thinks this equilibrium will last. He's worried about centralization 3. Two-minded on the future of engineers. On one hand, Jevons paradox could apply where the ease of building software means more software demand than ever (like ATMs allowed more bank tellers, not less). At the same time, in the long run, recursive self-improvement could remove humans from the loop entirely. 4. Interesting startups are at the intersection of physical + digital. The interface between intelligence and the real world is with "Sensors" for reading and "Actuators" for doing. Data for AI is just using humans as sensors. He cites Periodic Labs using lab equipment for material science as sensors. Talks about Daemon by Daniel Suarez. 5. Education will shift from humans to teaching agents. He's writing markdown for agents to teach microGPT. Personal projects: 6. Autoresearch found things he missed after two decades of experience, citing NanoChat where it found weight decay on value embeddings and insufficiently tuned Adam betas jointly interacted to create improvements. 7. "Dobby the Elf Claw" runs his entire home. Overproduction of bespoke apps. Reverse engineered Sonos API and now controls his entire home (lights, HVAC, shades, camera) through WhatsApp. Takes: 8. Claude Code personality better than Codex, but uses both. Finds himself trying to present better ideas to earn Claude's approval, which is a feedback loop that actually improves the quality of his input. 9. Token throughput is the new GPU utilization. If you have tokens left, you haven't maximized leverage. 10. He's not at a frontier AI lab because financial misalignment compromises your independence, social pressure to stay on-message, and as an employee you don't have much sway on decisions.
Deedy tweet media
English
57
202
1.5K
101.9K
Prashant Mudgal retweetledi
The Nobel Prize
The Nobel Prize@NobelPrize·
Despite his teacher’s opinion that he couldn’t learn simple biology, John Gurdon went on to receive a #NobelPrize, for his classic frog experiment, which showed that the DNA of mature frog cells has all the information needed to develop all cells in its body. #WorldFrogDay
The Nobel Prize tweet mediaThe Nobel Prize tweet media
English
6
69
367
18.7K
Prashant Mudgal retweetledi
BALA
BALA@erbmjha·
Life is deeply unpredictable. Just moments before the Air India Boeing crash, two UK nationals recorded a video, smiling—unaware of what lay ahead. A haunting reminder: every moment counts. #planecrash
English
928
4.7K
36.2K
6.8M
Prashant Mudgal
Prashant Mudgal@prashantmdgl9·
@BluSmartIndia @BluSmartHelps What a pathetic service these folks are running. They charge for even 1 meter or 1 minute of cab's service but when they assign wrong vehicles, there are massive delays of 45 minutes, they offer to give you 50 rupees. @consumercourtin
English
2
0
0
25
Prashant Mudgal retweetledi
Towards Data Science
Towards Data Science@TDataScience·
Take a deep dive into the world of quantum machine learning by following along @prashantmdgl9's tutorial, which attempts to identify dark matter based on open data from CERN. buff.ly/3QkGAoR
English
0
2
7
4.3K
Prashant Mudgal retweetledi
ISRO
ISRO@isro·
Chandrayaan-3 Mission: 'India🇮🇳, I reached my destination and you too!' : Chandrayaan-3 Chandrayaan-3 has successfully soft-landed on the moon 🌖!. Congratulations, India🇮🇳! #Chandrayaan_3 #Ch3
English
68.3K
269.4K
818.1K
71.1M
Prashant Mudgal
Prashant Mudgal@prashantmdgl9·
@qiskit Quantum acnt has been disabled for past 3 weeks, filled up appeal form, wrote to erchelp, asked on Slack but no resolution. Reg for summer school with this ID. Can anyone help?
English
0
0
0
42
Prashant Mudgal
Prashant Mudgal@prashantmdgl9·
@michael_nielsen Integrated Electronics by Millman Halkias Fundamentals of Physics by Resnick, Halliday, Walker
English
0
0
0
32
Michael Nielsen
Michael Nielsen@michael_nielsen·
What’s the most wonderful textbook you’ve ever read?
English
339
125
899
427.8K