Topden⚡ (@thirdpoler) header
Topden⚡ (@thirdpoler) profile picture

I do code.

Joined April 2013
Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)Photo by Topden⚡ (@thirdpoler)
Topden⚡ retweeted
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me. I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA. I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation. Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO. Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours. Jensen
59,090
120,014
24,229
1,148,819
54,804,749
Topden⚡ retweeted
We’re opening up access to Atlas to everyone today. We’ve built apps and API endpoints to help you use Atlas any way you can imagine: bring your ideas for building a 3D world and come away with keyframes, video clips, or 3D Gaussian splats.
140
489
241
4,271
541,188
Topden⚡ retweeted
Replying to @gxjo_dev
y’all should check insideout.sh
2
11
1
162
48,854
Topden⚡ retweeted
We’ll make sure your $12 is still there; we’ve already moved $12 from our own wallet to cover it.💁🏻‍♀️
Me reacting to the Binance Hack
971
604
171
11,675
921,581
Brutal!!! This is why we love @elonmusk – at Partridge Green, England
Elon Musk vs. the media: one man, unlimited fact-checking, and zero chill. 🤣
66
517
13
4,184
218,409
Websites for Designers. 1. balsa-ui.com 2. springs.studio 3. animos.app 4. gkurt.com/tegaki 5. meshfont.com Save for later.
5
54
565
25,063
106
408
28
7,371
1,049,579
Topden⚡ retweeted
Gentle reminder: Block out time away from the screen. Force yourself if you have to. Read a book for once. Hit the coffee shop. Do anything that gives your mind space to process all of the noise you've accumulated. You will feel the immense difference in mental clarity.
257
471
32
4,830
174,574
Topden⚡ retweeted
Replying to @petergostev
Can you explain to me how to fit Kimi K3 on my Mac?
1
1
26
2,821
Topden⚡ retweeted
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
2,938
7,398
2,223
61,100
22,038,575
Topden⚡ retweeted
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.
531
2,475
439
22,929
3,993,434
Defending my Spring Boot Java app that uses 64GB RAM to return { "status": "ok" }
71
710
52
11,079
543,447
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
2,554
7,301
2,906
55,185
17,115,136
call it dirty money, but i still donated $1m more than you did 🤷‍♀️ thank you for the opportunity #TeamWater
2,572
1,719
505
123,496
15,211,200
Topden⚡ retweeted
To celebrate the release of v0.app + agentic v0 we're launching "Free0" For the next 4 days, v0 is FREE! Each day we'll have challenges where you can earn more "Free0" by sharing your v0 creations. Challenge 1 threaded below👇
92
167
75
1,552
290,991
Say hello to the @geminicli, a local CLI to help you build and maintain software with 1,000 free Gemini 2.5 Pro requests per day : )
418
627
299
8,526
1,387,520
"Chatting" with LLM feels like using an 80s computer terminal. The GUI hasn't been invented, yet but imo some properties of it can start to be predicted. 1 it will be visual (like GUIs of the past) because vision (pictures, charts, animations, not so much reading) is the 10-lane highway into brain. It's the highest input information bandwidth and ~1/3 of brain compute is dedicated to it. 2 it will be generative an input-conditional, i.e. the GUI is generated on-demand, specifically for your prompt, and everything is present and reconfigured with the immediate purpose in mind. 3 a little bit more of an open question - the degree of procedural. On one end of the axis you can imagine one big diffusion model dreaming up the entire output canvas. On the other, a page filled with (procedural) React components or so (think: images, charts, animations, diagrams, ...). I'd guess a mix, with the latter as the primary skeleton. But I'm placing my bets now that some fluid, magical, ephemeral, interactive 2D canvas (GUI) written from scratch and just for you is the limit as capability goes to \infty. And I think it has already slowly started (e.g. think: code blocks / highlighting, latex blocks, markdown e.g. bold, italic, lists, tables, even emoji, and maybe more ambitiously the Artifacts tab, with Mermaid charts or fuller apps), though it's all kind of very early and primitive. Shoutout to Iron Man in particular (and to some extent Start Trek / Minority Report) as popular science AI/UI portrayals barking up this tree.
392
786
185
7,042
741,987