Lecturer @ University of Sri Jayewardenepura || DL Theory, GNN, Human Action Recognition, Network Science || British Humor || Rowing || Humanist

Sri Lanka
Joined November 2013
Sanka Mohottala retweeted
Son of a bitch this stings.
716
4,593
545
39,447
6,218,447
600km. Across Sri Lanka. On foot. 🇱🇰 British vet Dr Janey Lowes is taking on one seriously bonkers challenge, running the entire length of Sri Lanka to raise money for a new veterinary hospital for street dogs! 🐾 Through the heat, rain and mountains, she’s doing it all for the animals she’s dedicated her life to helping. We’ve previously worked with and raised money for @WECare_SriLanka during our tours to the country, so this is a cause that already means a lot to us ❤️ An incredible effort for an incredible cause. Show Janey some support, if you can! 👏 Full details here ➡️ tinyurl.com/ycym6ym4
8
89
3
447
21,287
Sanka Mohottala retweeted
Algorithms by Jeff Erickson - pair it along with this MIT's adv data structures. The illustrations are simply great, and this is one of the best algorithm books out there. jeffe.cs.illinois.edu/teachi…
MIT's 6.851: Advanced Data Structures (Spring'21) courses.csail.mit.edu/6.851/…
1
58
528
15,262
Sanka Mohottala retweeted
8
159
3
1,181
39,205
Sanka Mohottala retweeted
Hi all, I have a new result I'm excited to share. It turns out that *all existing implementations* of softmax and cross-entropy (that's JAX, PyTorch, textbooks, etc) have a subtle bug --- two bugs, actually. A simple rewrite fixes both, and eliminates "slingshots" when grokking:
135
791
148
6,483
789,031
Sanka Mohottala retweeted
To bring quantum applications within reach sooner, we must compress the circuits that power them. Join our @Kaggle competition to build efficient, verifiable circuits using our new open source kickmix library: goo.gle/4BqF2QX
9
60
13
357
18,258
Sanka Mohottala retweeted
University of Toronto's "Neural Networks for Machine Learning" by Geoffrey Hinton Videos: cs.toronto.edu/~hinton/cours… Slides: cs.toronto.edu/~hinton/cours…
146
1
723
20,830
Sanka Mohottala retweeted
全世界包括清北的编程课程都应该向斯坦福的CS146S Fall 2026看齐!这门课相比一年前的Fall 2025已经砍掉了85%的内容,可以知道编程领域进展有多恐怖了,如果还停留在教科书十年不需更新的幻觉中,可想而知会多落后了! 两版课纲我逐周对了一遍: 第 1 周:教你怎么写 prompt → 200 行代码手搓一个 Claude Code 期末项目占分:80% → 50% 给真实开源项目提 PR:0 → 30% 去年还单独讲一周的 AI IDE、Warp 终端、一句 prompt 生成整个应用,今年全部都拿掉。 取而代之的是 Agent Skills、CLAUDE.md / AGENTS.md / hooks、agent-ready 代码库、后台并行 agent、MCP portal 和模型路由,最后一周单独讲软件工厂。 刚入门的话,我建议从第 1 周跟起: 9/22 那节 200 行手写 coding agent,slides 和完整代码都公开了,最核心的是 agent 原型—— read / write / edit / bash 四个工具加一个循环 9/24 拆主流 coding agent 的 system prompt,原始 prompt 文件也已放出来 如果已经天天跟 coding agent 打交道,前几周大概率扫一眼就行,我会重点盯这几块: - 嘉宾:SpaceX SI负责人 @leerob、Claude Code之父 @bcherny 已经分享完,10/22 轮到 Factory 的 CTO @EnoReyes,后面还有 Cognition、Semgrep、Cloudflare、Replit 等的 @amasad 和 @eladgil - 第 9–10 周:大团队怎么落地,MCP portal、LLM gateway、模型路由、成本优化 - 前五周的阅读清单,凑起来就是一份 2026 版 agent 工程书单 30% 的开源分也很有意思:Vercel、Semgrep、OpenHands、Unsloth 等 15 个开源项目给学生做指导,PR 直接往生产级代码库里提,这在大学课程里还是头一回。 课程材料陆续公开,不是斯坦福学生也能跟:themodernsoftware.dev 后面几周的嘉宾分享我会边看边拆,关注我,第一时间同步最佳实践🫡
I’m excited to finally announce the newest edition my Stanford course 𝗧𝗵𝗲 𝗠𝗼𝗱𝗲𝗿𝗻 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿. It has been 9 months in the making. Last November, with the release of Claude Opus 4.5, coding agents experienced a step function improvement in capability. We all felt it. The LLMs were more powerful, could reason for longer, solve harder tasks. This year’s iteration of my course reflects the 2026 metamorphosis of software engineering. My core belief is simple: AI-native developers of the LLM era are going to become the most important members of any software organization. I have designed my course to train this next generation of engineers. 𝗪𝗵𝗮𝘁’𝘀 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝘁𝗵𝗶𝘀 𝘁𝗶𝗺𝗲 𝗮𝗿𝗼𝘂𝗻𝗱 First, 85% of my Fall 2025 class material is being thrown out. The Fall 2026 syllabus reflects the core capabilities AI-native engineers must have: agent skills, advanced context engineering, MCP portals, agent-ready codebase principles, agentic code review, security, parallelizing background agents, software factories, and more. Second, I am going to teach my students how to have software taste. Every student will be required to ship pull requests to production-grade, real-world codebases. The course is collaborating with the top open-source AI repos who will offer support and mentorship to students on how to meaningfully contribute to their projects. This has never been done before in any university course so I am incredibly grateful to our OSS Partners: @browserbase, @HeyGen, @CopilotKit, @semgrep, @OpenHandsDev, @milvusio, @marimo_io, Pi, @crewAIInc, @warpdotdev, @vercel, @cmux, @arizeai, @UnslothAI, and @anyscalecompute. 𝗪𝗵𝗮𝘁’𝘀 𝘀𝘁𝗮𝘆𝗶𝗻𝗴 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 I’m fortunate to again have AI software engineering leaders and founders as guest speakers to share their learnings from building top coding agent products. Thank you to @leerob from @cursor_ai, @bcherny of @claudeai code, @EnoReyes of @FactoryAI, @silasalberti of @cognition, @0xine of @semgrep, Rajesh Bhatia of @Cloudflare , @amasad of @Replit, and @eladgil. All resources will be available online. All classes will be available to the public. 9/22 on Stanford campus. See you in class.  themodernsoftware.dev/
166
716
26
3,618
233,725
Sanka Mohottala retweeted
Replying to @bitkinbiriisi @grok
29
20
4
1,702
408,988
Sanka Mohottala retweeted
I have discovered the the BEST way to get 3D modeling results from LLMs The app LiDAR scans the room while taking hundreds of high quality photos. Then a workflow + skill I've created models out every item recursively checking the model against the photo at the exact spot + angle where the photo was captured The result is a a dimensionally accurate and high quality model of your room All in my latest video on how to do it youtube.com/watch?v=JGQCcCzu…
189
233
59
4,258
479,837
Sanka Mohottala retweeted
A seal accidentally pops up and scares a polar bear cub while it was happily making snowballs
135
12,619
898
80,800
5,859,181
Sanka Mohottala retweeted
Book, Essential Mathematics for Convex Optimization by Fatma Kılınç Karzan & Arkadi Nemirovski www2.isye.gatech.edu/~nemiro… Introduction to Linear Optimization by Arkadi Nemirovski www2.isye.gatech.edu/~nemiro… Statistical Inference via Convex Optimization by Anatoli Juditsky & Arkadi Nemirovski www2.isye.gatech.edu/~nemiro…
23
147
4,865
Sanka Mohottala retweeted
Our book "The Elements of Differentiable Programming" can now be read directly in the browser: diffprog.github.io/
11
92
7
788
58,548
Sanka Mohottala retweeted
"Mathematical Theory of the Transformer" is an extensive, 825-page mathematical monograph exploring the theoretical foundations of Transformer architectures. It covers a remarkable range of topics, including embeddings and positional encoding, self-attention and multi-head attention, matrix decompositions, linear algebra, spectral analysis, information geometry, training dynamics, redundancy, optimization, and incremental Transformer architectures. This is an advanced, mathematically rigorous read for anyone interested in understanding the mathematical structures underlying Transformer-based AI systems, including modern generative AI. doi.org/10.5281/zenodo.20199…
29
265
16
1,724
72,328
Sanka Mohottala retweeted
Graph Machine Learning course Lecture 9 presents Graph Transformer 🌟 Graph Laplacian/random walk encoding, over-squashing, sparse/dense graph self-attention, trilinear edge features, hierarchical GT, heavy-edge matching, O(n) hierarchical attention. storage.googleapis.com/xavie…
2
32
1
311
9,895
Sanka Mohottala retweeted
We are trying to build a free LeetCode for AI researchers. You can learn how to code core ideas from important papers across various areas (e.g., LLMs, JEPA, RL, diffusion), contribute to the problem bank, and importantly, post your thoughts to find like-minded people for collaboration or job opportunities. Of course, the current version is still far from mature, so anyone who wants to help us with this project is welcome!
Preparing for AI Research Scientist interviews? 🔥 We just open-sourced PaperLeet 🐈‍⬛ LeetCode for AI researchers: implement the core of ~100 key papers (llm, rl, diffusion, flow matching, JEPA, world models), graded by tests that check the math. paperleet.com
40
179
4
1,950
79,824
Sanka Mohottala retweeted
Happy that arxiv.org/abs/2605.07113 was accepted at NeurIPS 2026. We propose a principled GNN architecture to compute primal- and dual-feasible SDP solutions and integrate them into an exact binary max-cut solver. This is a prime example of when expressive GNNs matter.
2
3
1
46
2,109
What a load of bs! Am I the only one who cant stand this guy?
46
Sanka Mohottala retweeted
He says the name just fine when he’s begging the Qataris for a personal jet or the Saudis for funding for his son-in-law’s private equity firm. Wonder what’s changed?
Trump on El-Sayed: "His name is actually Abduladadalalalala. It's Adulbabababababa Mohammed Al-Sayed. So his middle name is Mohammed. So I was right. He's a jihadist."
2,175
26,328
583
207,667
2,936,176