X

Articles from X

Cards List

@natolambert: New lecture for the book! Nominally about synthetic data, but mostly is a walk through of the distillation literature f…

X AI KOLs Timeline · 1h ago Cached

Natolambert announces a new lecture covering synthetic data and the history of distillation, from Hinton 2015 to modern on-policy distillation, with over 7 hours of video content.

0 favorites 0 likes

@zachlloydtweets: https://x.com/zachlloydtweets/status/2069428152338665622

X AI KOLs Timeline · 2h ago Cached

This post explains how to create an automated feedback loop for AI agents to iteratively improve their skills, using computer use and an observer skill to evaluate and update the skill code.

0 favorites 0 likes

@PaddlePaddle: PP-OCRv6 Tech Deep Dive Ep.1: In the Era of Large Models, Why Does Lightweight OCR Still Have Irreplaceable Value? — PP…

X AI KOLs Timeline · 2h ago Cached

PP-OCRv6 is a lightweight OCR model (34.5M parameters) that challenges large VLMs with its MetaFormer architecture, offering efficient text detection and recognition across multiple deployment scenarios.

0 favorites 0 likes

@AlphaSignalAI: https://x.com/AlphaSignalAI/status/2069424192274252094

X AI KOLs Timeline · 2h ago Cached

Microsoft's NextLat introduces a training objective that rewards belief-state representations instead of relying solely on next-token prediction, pushing models toward compact world models for better generalization.

0 favorites 0 likes

@analogalok: I just got Gemma 4 26B A4B MoE model running fully locally with Hermes agent on an 8GB RTX 4060 and it's now backtestin…

X AI KOLs Following · 2h ago Cached

A developer demonstrates running Gemma 4 26B MoE model locally on an 8GB RTX 4060 with Hermes agent to fully automate backtesting of trading strategies, highlighting the growing capability of local LLMs as autonomous agents.

0 favorites 0 likes

@no_stp_on_snek: what actually surprised me fine-tuning a small open model. note im failry new in this area so some of this may seem obv…

X AI KOLs Timeline · 3h ago Cached

A developer shares surprising lessons from fine-tuning a small open model, including that base models often already max out on intended improvements, the real weakness is behavior (caving), and fine-tuning requires careful measurement and balancing.

0 favorites 0 likes

@sydneyrunkle: interesting point here: loops amplify behavior, making them a double edged sword but we know loops are the future, so h…

X AI KOLs Following · 3h ago Cached

Discussion on how loops in AI agents can amplify both good and bad behaviors, emphasizing the need for an engaged human in the loop to guide the agent's learning of user preferences.

0 favorites 0 likes

@jasonzhou1993: https://x.com/jasonzhou1993/status/2069413003897012435

X AI KOLs Timeline · 3h ago Cached

Crabbox is a new tool that gives AI coding agents isolated cloud environments to test and verify PRs, enabling them to work in parallel without conflicts and reducing the review bottleneck.

0 favorites 0 likes

@Fenng: Tencent QQ Mail Agently Mail, a dedicated email service customized for Agents. Tencent is going all out https://agent.qq.com

X AI KOLs Following · 3h ago Cached

Tencent launches Agently Mail for QQ Mail, a dedicated email service tailored for AI Agents.

0 favorites 0 likes

@ChadJonesEcon: Some news: As of June 30, I'll be on leave from Stanford at Anthropic. I'm joining the Anthropic Institute, where I'll …

X AI KOLs Following · 3h ago Cached

Chad Jones announced he will be on leave from Stanford starting June 30 to join the Anthropic Institute, where he will continue research on AI and economic futures.

0 favorites 0 likes

@PrajwalTomar_: https://x.com/PrajwalTomar_/status/2069409824824316060

X AI KOLs Following · 3h ago Cached

The author built a fully offline AI agent using local embedding models, Llama via Ollama, and VectorAI DB to address the risks of cloud-dependent AI. The agent runs on an 8GB MacBook, processes sensitive documents, and maintains memory across sessions.

0 favorites 0 likes

@omarsar0: Cross Repo Review maps how your repos depend on each other. Then on every PR, it reads the related repos and surfaces d…

X AI KOLs Following · 4h ago Cached

Cross Repo Review is a tool that maps inter-repo dependencies and surfaces downstream impacts, breaking changes, and blast radius on PRs, tracking code, service, data, and pipeline dependencies.

0 favorites 0 likes

@omarsar0: Most AI code review tools look at one repo at a time. But the bug usually isn't in the code that changed. It's in what …

X AI KOLs Following · 4h ago Cached

QodoAI released Cross Repo Review, an AI code review tool that can detect bugs across multiple repositories, going beyond single-repo analysis to catch issues caused by changes in one repo that break others.

0 favorites 0 likes

@nielskle: Vibe coding funnels is making marketers broke. It should be making them rich. Introducing the Perspective MCP: Enable C…

X AI KOLs Timeline · 4h ago Cached

Introducing the Perspective MCP, a tool that enables Claude to build conversion funnels with tracking, CRM, and auto optimization, built on experience from $1B in ad spend.

0 favorites 0 likes

@snscaimito: Well... Software development has always changed in the last 50 years.

X AI KOLs Following · 4h ago Cached

AI has automated the coding process, shifting the software developer's role from writing code to specifying and verifying systems, effectively returning the focus to product development.

0 favorites 0 likes

@vanstriendaniel: It's raining OCR models again! @Baidu_Inc's Unlimited-OCR is one of the more interesting. You can try it without much e…

X AI KOLs Following · 4h ago Cached

This post shows how to serve Baidu's Unlimited-OCR model as a temporary, OpenAI-compatible endpoint on Hugging Face Jobs, enabling multi-page document parsing with features like table-to-HTML and equation-to-LaTeX extraction.

0 favorites 0 likes

@AYi_AInotes: https://x.com/AYi_AInotes/status/2069399806502453264

X AI KOLs Timeline · 4h ago Cached

A beginner-friendly tutorial on how to set up persistent memory for an AI Agent in 30 minutes, using the open-source EverOS tool to store memory as editable Markdown files, without requiring Docker or vector database clusters.

0 favorites 0 likes

@arcane_bloom: The Shift from Software Engineering to Agent Engineering: A 5-Part Breakdown 1/6 Most developers fail when building AI …

X AI KOLs Timeline · 4h ago Cached

A thread explaining the 5 core mental shifts needed to transition from traditional software engineering to agent engineering, emphasizing why conventional patterns like hard-coded routes and binary tests fail with AI agents.

0 favorites 0 likes

@SergioPaniego: we let an agent train a coding agent, live, from one prompt which agent is which, why it makes sense, and every artifac…

X AI KOLs Timeline · 5h ago Cached

A live demonstration of an AI agent training a coding agent from a single prompt, with all artifacts recapped.

0 favorites 0 likes

@boshen_c: Time to unmask the man behind this work! @Shanshrew has created a novel parser architecture which is 2x - 3x faster. Pl…

X AI KOLs Following · 5h ago Cached

A novel parser architecture developed by Shanshrew achieves 2-3x speedup over the current fastest JS/TS parser, and is being integrated into Oxc.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback