Syed Refat Al Abrar

Holy Opus 5 🤯 i think you people never saw this level of creativity and @threejs use ever music , sound , blackhole everything is procedurally generated no external assets Prompt : Please develop a single, self-contained HTML file featuring an extraordinary 3D audio visualizer. The visualizer should be driven by a full-length, highly catchy EDM/dubstep track titled 'SINGULARITY', seamlessly integrating the audio playback with dynamic, high-performance 3D visual effects.

On the Chartography benchmark (100 questions over dense real-world charts), Fable 5's accuracy goes from 29% to 73% with a zoom tool, and Sonnet 5’s from 13% to 44%. See the cookbook to learn more: github.com/anthropics/cla…

On several coding and knowledge work evaluations, Opus 5 is the new state-of-the-art:

We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. x.com/i/article/2080…

Introducing Claude Opus 5. It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by every country. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. The world needs both frontier closed models and frontier open models. images.nvidia.com/pdf/Open-Weigh…

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential. OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose. @rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think! Try it out: openworker.com (requires your own API key) Source code: github.com/andrewyng/open…

ANTHROPIC LAUNCHES OFFICIAL CLAUDE CODE PROMPT LIBRARY Anthropic released an official prompt library for Claude Code. Access pre-built templates that demonstrate how Anthropic structures context, instructions, and reasoning for developers.

proud to share that herdr is moving to apache 2.0. 🎉 the master branch is now apache 2.0, and the next release will ship under it. this removes the biggest adoption blocker for many teams and makes the herdr runtime open for everyone to build on. one terminal. whole herd.🐏

The Claude Security plugin for Claude Code is now available in beta. Scan your changes for vulnerabilities before you commit, or run a full scan across your codebase, all from your terminal on the Claude inference you already run.

Backpropagation by hand ✍️ ~ 11 steps walkthrough below Backpropagation is the algorithm that actually trains a neural network, and it is where most people stop following along. It is not calculus you cannot do. It is matrix multiplication, working backward, one layer at a time. So I drew and calculated one entirely by hand. Goal: push the loss gradient back through a 3-layer network and land on a new value for every weight and bias. = 1. Given = A 3-layer perceptron, an input X, predictions Ypred = [0.5, 0.5, 0], and the truth Ytarget = [0, 1, 0]. = 2. Backprop gradient cells = Let us draw empty cells for every gradient we are about to compute. The shape of the answer comes first. = 3. Layer 3 softmax = We get dL/dz3 straight from Ypred minus Ytarget = [0.5, -0.5, 0]. No chain rule needed, and that shortcut is the whole reason softmax and cross-entropy are paired. = 4. Layer 3 weights and biases = Let us multiply dL/dz3 by [a2 | 1]. One multiplication gives the gradient for W3 and b3 together. = 5. Layer 2 activations = We multiply dL/dz3 by W3 to get dL/da2. The gradient moves back across a layer the same way the signal moved forward. = 6. Layer 2 ReLU = Let us pass it through the gate: keep the gradient where the activation was positive, zero it everywhere else. = 7. Layer 2 weights and biases = We multiply dL/dz2 by [a1 | 1]. The same figure as step 4, one layer up. = 8. Layer 1 activations = Let us multiply dL/dz2 by W2. = 9. Layer 1 ReLU = We apply the same gate again, now on a1. = 10. Layer 1 weights and biases = Let us multiply dL/dz1 by [x | 1], and every weight in the network now has a gradient. = 11. Update = We subtract, and the network has learned. In practice a learning rate scales this step. The gradients: dL/dz3 = [0.5, -0.5, 0] dL/da1 = [1, -2, 2, -1] dL/dz1 = [0, -2, 2, -1] The takeaway: matrix multiplication is all you need. Just like the forward pass, backpropagation is matrix multiplications end to end. You can do every one by hand, slowly and imperfectly, which is exactly why a GPU's ability to do them fast mattered so much to deep learning. 💾 Save this post!

@lydiahallie Infinite context 👻

What's your #1 Claude Code feature request?

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model. Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.

In 1948, Claude Shannon invented the math behind every LLM you use today. He tested it by making his wife guess the next letter in a book. A Stanford-trained mathematician just released a 32-minute walkthrough of this exact history - and why the "next-token prediction" story of GPT-5 is actually wrong. Bookmark & watch this weekend. The alternative is a graduate info-theory course + 3 semesters of your life.

@lydiahallie @ruchernchong That will not be deterministic right!

@ruchernchong Ah you can't do that with the memory field alone, but you can add it to the agent's instructions. E.g. you can set memory to `project` and add some instructions like "Also read <path to user prefs>..."

💡 You can give subagents persistent memory via the "memory" field A subagent doesn't inherit the main session's auto memory, it forgets everything between runs. This field gives it its own dir across sessions Memory loads before starting & the agent writes back for next time

@kunchenguid No Opus 🫠

choosing an LLM subscription these days is almost like making a hiring decision - much lower stakes obviously, but surprisingly nuanced after using many of the frontier models heavily, here’s the mental model I’ve developed: Grok 4.5 is James Bond: fast, versatile, and gets your shit done. the grok subscription also gives you image and video generation. the grok build harness gives you free access to X. the true jack of all trades GPT 5.6 Sol is Mr. Spock: the trustworthy architect and systems engineer. you don't go to it for aesthetics and personality. but it will reason through every edge case and give you the most rigorous solution. (and sometimes rewrite your entire codebase for fun) Claude Fable 5 is Winston Wolf: the legend you call to fix your hardest problems. you wish you can have the wolf around all day, but no you can't Kimi K3 is Winston Wolf’s younger brother: not quite the legend, but learned enough tricks to be a substitute GLM 5.2 is an army of Minions: affordable enough to help you move mountains through sheer volume. just be prepared to supervise some chaos

Baidu just open-sourced an OCR model that reads entire 40-page documents in one shot. It's called Unlimited-OCR. 3 billion parameters but only 500 million active during inference. Runs 100% locally on your machine. Why this matters: traditional OCR tools chop documents page by page. Tables that span two pages break. Reading order gets lost. Cross-page context disappears. Unlimited-OCR processes the whole document at once. 32K context window. Text, formulas, tables, reading order all preserved across pages. Output comes out as clean structured Markdown. → 93% accuracy on the standard benchmark. +6 points over the baseline. → Error rate stays below 0.11 even past 40 pages. → Multilingual out of the box. → 2.12 million downloads on Hugging Face last month. 14,600 GitHub stars. For context: Amazon Textract, Google Cloud Vision, and Azure Document Intelligence all charge per page. This runs locally for free.