Anshul

2K posts

Anshul banner
Anshul

Anshul

@curiousAnshul

Tech enthusiast and Software engineer who enjoys 🎮 🏏 🎞️ 📚

Katılım Ağustos 2013
253 Takip Edilen76 Takipçiler
Anshul
Anshul@curiousAnshul·
I'm so impressed with Pi Agent! It's simple, beautiful, and incredibly powerful. Truly engineering at its peak. Huge thanks to @badlogicgames for creating such an amazing tool! 🚀✨💻
English
0
0
5
594
Anshul
Anshul@curiousAnshul·
@kenwuuuu They have already launched a new framework
English
0
0
1
68
Ken Wu
Ken Wu@kenwuuuu·
so what is the current industry standard to build agents? do people still use langchain/langgraph?
English
128
27
1K
261.4K
Anshul
Anshul@curiousAnshul·
@paraschopra I agree. In my views Poetry and shayari are great examples of this — a few structured words can compress emotions, context, and imagery that might otherwise take pages or even visuals to fully express.
English
0
0
1
21
Paras Chopra
Paras Chopra@paraschopra·
A picture might be worth a thousand words, but it is often more efficient to send those 1000 words instead of a picture. Words are highly compressed representations of reality. Hence, intelligence lies in the structure of language itself, perhaps not so much in a model of it.
English
22
5
137
7.6K
Anshul
Anshul@curiousAnshul·
@karpathy Congratulations 👏👏👏
English
0
0
0
13
Andrej Karpathy
Andrej Karpathy@karpathy·
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
English
7.9K
11.1K
149.1K
27.1M
Physics In History
Physics In History@PhysInHistory·
In your opinion, what is time ? ✍️
English
355
13
163
28.8K
Anshul
Anshul@curiousAnshul·
One thing I realized after reading your articles(Gbrain) is that, in the future, software will definitely have an LLM layer that will mainly act as a reasoner. Engineers and coding agents will write tools and skill files, and the software will expose a reasoning layer on top of them. Humans will simply describe what they want, and the reasoning layer will decide which tools to use. In current systems, like booking websites, users have to follow certain steps and clicks to complete a task. But sooner or later, almost every website and application will have a chat-like interface where users will simply describe what they want, and the software, along with the LLM reasoning layer, will identify and execute the required steps automatically. What do you think? @garrytan
English
0
0
1
21
Garry Tan
Garry Tan@garrytan·
Realization: in the past, we wrote code to call LLMs Today, we write prompts and skill files for LLMs to execute code. Tomorrow? Yet unwritten. We will find out soon.
English
181
43
781
52K
Anshul
Anshul@curiousAnshul·
@garrytan One interesting thing I learned from this article is that when you and an agent collaboratively solve a problem, it’s valuable to turn that solution into a skill file so the agent can apply that learning in future tasks. Great Article !!!
English
0
0
0
4
Reads with Ravi
Reads with Ravi@readswithravi·
What’s a book that you will never stop recommending?
English
133
19
151
37.5K
Anshul
Anshul@curiousAnshul·
An AI reading companion that helps people understand books without interrupting their reading. Instead of stopping to open Google or ChatGPT whenever they get confused by a word, idea, person, or paragraph from the book, users upload the PDF of the same book into the app once. Then while reading, they can simply ask things like “I’m on page 8 line 10” or “explain paragraph 5 of page 8,” and the app finds that exact part of the book and with the help of gpt it explains what the author is trying to say in a simple and clear way, along with extra information whenever needed.
English
0
0
0
232
Sam Altman
Sam Altman@sama·
i would like to talk to people who have built amazing things with 5.5 that weren't possible with earlier models. i am especially interested in examples that took ludicrous token budgets. thanks.
English
1.7K
267
8.4K
914.6K
Google AI
Google AI@GoogleAI·
I/O is less than 3 weeks away 🤯 We want YOU to help us create the countdown that will play before the keynote begins. Using @GoogleAIStudio or Canvas in @GeminiApp vibe code your most creative countdown concept and send it to us by May 6th. The only rule is that your build has to feature a large number between 1 and 10. Check the replies in this thread for sample projects to draw inspiration from or remix. You can find more info and directions on how to submit your builds here: goo.gle/codethecountdo…
GIF
English
70
79
670
132.4K
rushilshah
rushilshah@rushilshah_x·
figma is the greatest design tool ever made
English
20
17
159
17.2K
Anshul
Anshul@curiousAnshul·
@Tekeee Yes Yes Yes .....100000 times yes
English
0
0
0
4
Tekee
Tekee@Tekeee·
HOT TAKE: Gaming is healthier for your brain than endless social media scrolling.
English
497
2.8K
36.7K
633.8K
Anshul
Anshul@curiousAnshul·
@boona11 How you are doing this, this deserves a tutorial 🙏🙏
English
1
0
2
182
Ibrahim Boona
Ibrahim Boona@boona11·
Built this fully in #threejs. Zero baked clips. whales, sharks, and fish schools are all procedural, turning, swimming, and banking in reaction to the world every frame. Notice how they flee smoothly from the cursor. Link -> reef-dive-game.netlify.app
English
13
22
341
32.4K
Microsoft Learn
Microsoft Learn@MicrosoftLearn·
Do NOT doom scroll tonight. Instead, learn a new skill. Comment for a course recommendation.
English
5.4K
2K
26.5K
1.4M
Anshul
Anshul@curiousAnshul·
@ClementDelangue @Gradio @TIME Huge congratulations to @huggingface — they’re not just democratizing AI, their courses are genuinely top-notch. A big part of my AI learning comes from them.
English
0
0
0
19
clem 🤗
clem 🤗@ClementDelangue·
Great to be included in the @TIME 10 Most Influential AI Companies of 2026! Let's go open-source AI!
clem 🤗 tweet media
English
33
42
340
25.8K
Paras Chopra
Paras Chopra@paraschopra·
Woke up to see my paper accepted at ICML 2026 :) 🕺🏽🚀 My first one at an A* conference! This position paper was a result of me deep diving into the philosophy of science to figure out what counts as “understanding something”. This drove me to Wittgenstein, Quine, William James and other Pragmatism advocates. I then applied what these philosophers talk about to the field of AI, and recommend how to make sense of ambiguous (and often metaphysically loaded) questions such as “what is AGI” or “can LLMs feel emotions”. Philosophical clarity is a necessary prerequisite for attacking unsolved problems, and I’ve found Pragmatism to be the most sensible position for making progress as its focus is always on empirical consequences of concepts (and not their metaphysical status). Will release the paper soon!
Paras Chopra tweet media
English
32
21
614
24.9K
Reads with Ravi
Reads with Ravi@readswithravi·
What’s the shortest book that had the biggest impact on you?
English
242
14
254
65.5K
Anshul
Anshul@curiousAnshul·
@angular Zone.js ⏳ async task starts ↓ 📦 zone.js tracks it ↓ ✅ task completes ↓ 🚨 zone says: "Something changed!" ↓ 🔄 Angular runs change detection ↓ 🖥️ UI updates
English
0
0
0
165
Angular
Angular@angular·
Challenge time! 🏆 Can you explain Dependency Injection or Zone.js using only emojis and simple words? Help a fellow developer understand a complex concept in the most creative way possible. Best explanation gets a virtual high-five 🖐️✨
English
11
4
57
10.5K