Pinned Tweet
Friends,
Following the recent changes to Twitter/X’s API model, we initially faced significant disruptions that affected our ability to deliver real-time trend snapshots. At the time, we raised concerns around accessibility and fairness for developers and researchers.
Since then, X has introduced a pay-per-use API model, providing a clearer and more flexible path forward. In light of this, we’ve decided to move ahead constructively and resume our operations on the platform.
We’re pleased to share that PulsarWave is back.
We have re-integrated with X’s API services, and I’ve personally resubscribed to X Premium to support continued development and stability.
Our focus remains unchanged: advancing #DataDemocracy and delivering high-quality insights to our users.
More updates on the new PulsarWave version coming soon. Stay tuned.
1,297
Kan Yuenyong retweeted
複雑な業務フローを3Dにしたら面白いかなーと思ってやってみたら、メトロ地図みたいになった。
受注数の変動によってどこでスタックする可能性があるのか、システム停止するとどうなってしまうのかが可視化できます。
みにくいけど、リアルな業務ってこんな感じだよなーと思いにふけました。
Kan Yuenyong retweeted
BREAKING: Cyberattack hits JPMorgan Chase, Visa, and Mastercard, leaking personal data of thousands of customers, per company statements.
More than 16,000 customer emails, some with phone numbers and account IDs, tied to the invitation-only Reserve program for clients with $10M+ assets under management were leaked.
A free online book: LLM Inference Handbook by Sherlock Xu (2026).
This book is a practical technical reference for engineers deploying, scaling, and operating language models in production.
It brings together the concepts and decisions involved in turning a trained model into a responsive, cost-aware service, from model behavior and hardware selection to application interfaces and ongoing operations.
Readers can use it as a guided progression or as a lookup resource for specific engineering questions.
Read the book online on @ChapterPal: chapterpal.com/book/3fef12a8…
Kan Yuenyong retweeted
RAG is officially cooked.
Researchers proved you can stuff 1 billion triple knowledge graph directly into an LLM using only 20GB of VRAM.
no vector DB, no Pinecone bill, no chunking nightmares.
Researchers introduced AtlasKV, and it makes the entire RAG pipeline look ancient.
Instead of bolting an external search engine onto an LLM, AtlasKV integrates billion-scale knowledge graphs directly into the model's inherent attention mechanism.
Using two new methods (KG2KV and HiKVP), it translates knowledge graph triples straight into the AI's internal memory with sub-linear time and memory complexity.
And the numbers are ridiculous:
• 1 billion knowledge triples integrated at scale
• Runs on less than 20GB of GPU VRAM
• Zero external retrievers
• Zero bloated context windows
• Zero retraining required when you add new knowledge
It maintains strong grounding and generalization without paying the latency tax of searching and reading massive prompts.
We spent years building clunky, fragile retrieval pipelines just to help AI look things up.
Kan Yuenyong retweeted
A knowledge graph schema means little if bad relationships can still get written. TypeGraph 0.75 adds enforced cardinality, acyclic relationships, cascading deletes, and schema validation. Particularly relevant when AI agents are modifying your data.
typegraph.dev/blog/an-ontolo…
Kan Yuenyong retweeted
The links between neuroscience and AI run deep: the first artificial neural network models were inspired by the brain. @StanfordBrain and @StanfordHAI have awarded their second round of AI and Neuroscience Grants to five teams: hai.stanford.edu/news/resear…
Kan Yuenyong retweeted
The next 12 months will bring AI shifts across strategy, operations, talent, technology, investment and governance.
In this live webinar, Distinguished VP Analyst Mary Mesaglio breaks down the 8️⃣ strategic AI themes every leader should understand to make better decisions and focus on what will matter most in the years ahead: gtnr.it/4C28uwV
Kan Yuenyong retweeted
Ontologies for AI in practice: Do LLMs need ontologies, or are text definitions good enough?
A three-part experiment on a small, deliberately ambiguous genealogy dataset (fictional people) tested what changes when an LLM is given progressively more semantics.
The task: count a person’s ancestors. The evidence is anecdotal by design, but practical.
🔎 Part I: adding semantics step by step
Data alone: many errors, and a correct count only by chance
Cleaner dates: no change
Plain-text definitions: a substantial improvement
RDF knowledge graph: the same answer, but it exposed hidden assumptions, including an imprecise question (“how many ancestors in this dataset?”)
Curated graph: more precise and consistent answers
Ontology: the correct count
🧪 Part II: model size and stability
Small local models (4B to 8B) could not use added semantics
Impact started to appear at 32B parameters
Text definitions produced high variability across runs
Knowledge graphs with ontologies matched or beat definitions and were more consistent
Removing the text definitions from context improved graph-based results
🧩 Part III: how to provide semantics
OWL axioms only, OWL with definitions, OWL with operational directives, Apache Ossie (OSI) and Google’s OKF were compared.
Takeaways:
- Axioms alone were not enough, and the natural-language definitions inside ontologies did most of the work
- With a capable model, the format mattered little. Opus reached perfect results across representations, while DeepSeek-R1:32B used none of them
- Ontology plus knowledge graph was the most effective and consistent option
- Among approaches that annotate data directly, OKF ranked highest
Definitions alone are not enough. Results were strongest when context-specific meaning is connected to the data elements themselves, as in a knowledge graph.
By Andrea Splendiani
Ontologies for AI in practice / part I sbee.link/gkx3nd6rec
Ontologies for AI in practice / part II sbee.link/erhmudfwc6
Ontologies for AI in practice / part III sbee.link/3d7xhwbnm4
#LLM #FAIRData #OWL #SemanticLayer #DataGovernance
--
Missed a talk at #CDL26? Or missed the whole thing?
All talk recordings will be available in the next few days.
With this many ideas and speakers, nobody could catch them all live
✅ Were you there? Replays included in your ticket
🎟 Couldn’t make it? Get a remote ticket for permanent on-demand access
sbee.link/pqwxhda3n4
Kan Yuenyong retweeted
This classic FREE 280-page PDF report from @JPMorgan provides an excellent framework for Machine Learning, AI, and Data Science investors, including an overview of types of alternative data and a brilliant tutorial on ML methods to analyze the data: cpb-us-e2.wpmucdn.com/facult…
Kan Yuenyong retweeted
Google 开源了一套多 Agent 写论文工具,从研究思路和实验记录直接生成 LaTeX 论文初稿。
项目叫 PaperOrchestra,由 Google Cloud AI Research 团队开发。
它把论文写作拆给多个专业 Agent:
大纲 Agent:整理研究思路,生成论文结构
文献 Agent:检索、筛选并整合相关论文
写作 Agent:分章节生成正文
修改 Agent:审查并优化内容
绘图 Agent:根据实验数据生成图表
支持会议 LaTeX 模板,可配置 Gemini、OpenAI 等模型。
需要注意:项目尚未提供配套数据集,生成内容仍需人工核实引用、实验结论和学术原创性。
GitHub:github.com/google-research/p…
你觉得 AI 写论文最难替代的是文献综述、论文写作,还是研究创新本身?
#AI #Agent #科研 #开源
📚 Learning Cybersecurity Fundamentals: A Practical Guide to Essential Cybersecurity Concepts
✍️ Author: Nicole Dove
📖 Get the book:
link.amazon/B0fFXA9Uf
🔐 Cybersecurity is now business-critical. Start your journey with the NIST 2.0 Cybersecurity Framework and align your skills with in-demand roles.
Description:
A practical guide that demystifies cybersecurity team structures and core principles. With clear explanations, relatable examples, and chapter-end quizzes, build foundational skills in threat detection, data protection, access management, and more.
🎯 Perfect for students, early-career professionals, and career changers.
#CyberSecurity #InfoSec #NIST #CyberCareers #SecurityFundamentals #DataProtection #CareerChange
Kan Yuenyong retweeted
These are literally the best visual resources for learning how Transformers, LLMs, embeddings, diffusion, and inference work ↓
1/ Transformer Explainer - Watch GPT process text through embeddings, attention, MLPs and next-token prediction.
poloclub.github.io/transform…
2/ Brendan Bycroft’s LLM Visualization - Explore an LLM from architecture down to tensors and operations.
bbycroft.net/llm
3/ 3Blue1Brown - Visual intuition for linear algebra, neural networks, backprop, attention and Transformers.
3blue1brown.com/topics/neura…
4/ The Illustrated Transformer - One of the clearest visual explanations of embeddings, Q/K/V and attention.
jalammar.github.io/illustrat…
5/ TensorFlow Playground - Watch neural networks learn as you change layers, activations, features and learning rate.
playground.tensorflow.org
6/ Google PAIR AI Explorables - Interactive explainers on LLMs, generalization, interpretability and model behavior.
playground.tensorflow.org
7/ Distill - Exceptional visual essays on t-SNE, feature visualization, GNNs and interpretability.
distill.pub
8/ Abhik Sarkar’s Transformer Visualizations - RoPE, KV cache, FlashAttention, MQA, GQA and more.
playground.tensorflow.org
9/ Visual Guide to Attention Variants - MHA, MQA, GQA and MLA visually compared.
magazine.sebastianraschka.co…
10/ Visual Guide to Mixture of Experts - Routing, experts, sparse activation and load balancing.
newsletter.maartengrootendor…
11/ Modular LLM Inference Handbook - Prefill, decode, KV cache, batching, quantization and speculative decoding.
handbook.modular.com/llm-inf…
12/ Apple Embedding Atlas - Explore clusters, neighborhoods and outliers in large embedding spaces.
apple.github.io/embedding-at…
13/ Diffusion Explainer - Follow Stable Diffusion step by step.
poloclub.github.io/diffusion…
14/ Neuronpedia - Explore features, activations, SAE latents and attribution graphs inside real models.
neuronpedia.org
15/ Seeing Theory - Probability, Bayes, distributions, regression and inference made interactive.
seeing-theory.brown.edu
16/ CNN Explainer - Visualize convolutions, feature maps, activations and pooling.
poloclub.github.io/cnn-expla…
17/ GAN Lab - Train a GAN in your browser and watch its generated distribution evolve.
poloclub.github.io/ganlab/
Save this. There’s a serious AI curriculum hiding inside these links.
Kan Yuenyong retweeted
Handbook on Harness Engineering for AI Agents [29-page PDF]: arxiv.org/pdf/2607.13285
Banger paper from Google on RSI.
(bookmark it)
They propose an approach for continual recursive self-improvement at the harness level. They also propose their own self-improving memory system for the harness optimizer.
This clearly highlights the importance of traces and having a functional, adaptive, and structured persistent memory system in your harness.
They show that a harness optimizer improves 9 of 10 continued runs when it remembers why it made each past edit.
They discuss that a common problem shows up when you change the model or the benchmark. An Opus-evolved harness started at 68.41 on Gemini, below the 73.89 of the plain seed harness.
Self-Improvement Memory groups past edits by the harness problem they addressed. For each edit, it stores the rationale, predicted outcome, observed outcome, and evaluation context. The proposer and the selector both read it before making new changes.
Across four domains, including Terminal-Bench 2.1 to Terminal-Bench 4, SIM beats continuing from the harness alone in six cross-dataset and four Opus-to-Gemini settings. Across ten coding runs, it adds 2.36 points on average (p=0.003).
If you evolve harnesses automatically, store the reasons and results of each edit next to the code.
arxiv.org/abs/2611.18856
Chat with Paper: academy.dair.ai/papers/self-…
Kan Yuenyong retweeted
BREAKING: Nvidia, $NVDA, has removed all affiliation with Jensen Huang on X.
Elon Musk says he will be gifting Jensen Huang a blue checkmark.
Self-improving AI is one of the most discussed ideas right now.
This is one of the most exciting papers I've read recently on the topic.
(bookmark it)
It proposes AutoRL, which lifts Qwen3 on AIME 2024 from 46.67% to 66.67% by letting agents supervise a live RL run instead of following a fixed recipe.
AutoRL works like an RL researcher on call.
Perceptor agents watch training curves, rollouts, and evaluations and flag problems. Three Proposer agents diagnose the issue and suggest changes. An Orchestrator approves them and applies them with a hot update or a restart from a checkpoint.
On math, AIME 2025 and HMMT 2025 each improve by 11.67 points. On agentic coding with LongCat-Flash-Lite, pass@1 rises from 52.29% to 65.13% over a long unattended run with interruptions.
Given a deliberately broken recipe, AutoRL found and fixed the problems.
The authors say agents can already handle routine RL supervision. Validating each change still takes a lot of compute.
arxiv.org/abs/2611.17790
Chat with Paper: academy.dair.ai/papers/autor…
Kan Yuenyong retweeted
‼️ Japan's cyber response team has found about 1,000 servers it suspects are bases for AI-run attacks on websites worldwide.
Most run AI pentest tools such as ARTEX. They appear to scan sites for flaws and try to steal config files.
One held traces of an Anthropic coding tool.
Kan Yuenyong retweeted
Understanding system design helps you build better apps, even when vibe coding.
Better architecture decisions. Better AI prompts. Fewer surprises when your app grows.
So I built an interactive app to learn system design visually.
designed-to-scale.vercel.app
Agentic Mesh: The GenAI-Powered Autonomous Agent Ecosystem
📕 Get Now: link.amazon/B09STyVj7
































