56 loops of Claude Code just killed every hand-crafted AI attack method. Anthropic just open-sourced a repo called Claudini. It uses Claude Code in an autoresearch loop to automatically discover new adversarial attacks against LLMs. After 56 iterations, it found an
LLMS
-
Disco GenTabs: From Information Browsing to AI-Generated Interfaces
By
–
This is powered by Gemini 3. The experiment is called Disco.
The feature is GenTabs. The big shift is this: We move from browsing information
→ to generating interfaces. AI is no longer just answering questions. It is assembling software on demand. -

Achieving 78.9% on OS-world, Outperforming GPT-5.4 at Lower Cost
By
–
Ngl, reaching 78,9% on OS-world and outperforming even GPT-5.4 at 1/10 cost is a big deal
-
Ollama Gets MLX Support in Recent Update
By
–
Haha, but what's not April's fools is that ollama finally got MLX support the other day
-
Using Sonnet for Judging: A Practical Alternative
By
–
Interesting idea! You can also just use Sonnet for judging, it is pretty good by itself
-

Build a Large Language Model from Scratch Repository
By
–
If you found it useful, reshare it with your network Follow me → @Sumanth_077 for more insights and tutorials on AI Engineering! nitter.net/Sumanth_077/status/203… Sumanth (@Sumanth_077) Build a Large Language Model from scratch! This repository contains the code examples for developing, pretraining, and finetuning a LLM from scratch. It is the official codebase for the book Build a Large Language Model (From Scratch). Notebook examples are included for each chapter: Chapter 1: Understanding Large Language Models Chapter 2: Working with Text Data Chapter 3: Coding Attention Mechanisms Chapter 4: Implementing a GPT Model from Scratch Chapter 5: Pretraining on Unlabeled Data Chapter 6: Finetuning for Text Classification Chapter 7: Finetuning to Follow Instructions Link to the repo in the comments! — https://nitter.net/Sumanth_077/status/2039332313910383043#m
→ View original post on X — @sumanth_077, 2026-04-01 13:22 UTC
-
GitHub Repository: LLMs from Scratch by Sebastian Raschka
By
–
Github Repo: github.com/rasbt/LLMs-from-s…
→ View original post on X — @sumanth_077, 2026-04-01 13:21 UTC
-

Build Large Language Models from Scratch: Complete Book Repository
By
–
Build a Large Language Model from scratch! This repository contains the code examples for developing, pretraining, and finetuning a LLM from scratch. It is the official codebase for the book Build a Large Language Model (From Scratch). Notebook examples are included for each chapter: Chapter 1: Understanding Large Language Models Chapter 2: Working with Text Data Chapter 3: Coding Attention Mechanisms Chapter 4: Implementing a GPT Model from Scratch Chapter 5: Pretraining on Unlabeled Data Chapter 6: Finetuning for Text Classification Chapter 7: Finetuning to Follow Instructions Link to the repo in the comments!
→ View original post on X — @sumanth_077, 2026-04-01 13:21 UTC
-

LaPha: AI Agents Think Exponentially Better in Poincaré Space
By
–
How can we give AI agents exponentially more room to think and solve complex problems? Researchers from Shanghai Academy of AI for Science, CMU, and others unveil LaPha. This new method trains AlphaZero-like LLM agents in a unique "Poincaré latent space." It leverages negative
-
Hidden thinking tokens reduce AI response usefulness by 40 percent
By
–
if you hide the thinking tokens that generated my AI's response you lower its usefulness to me by 40%
