Image created with Flux Pro v1.1 Ultra. Image prompt: Giant “100” as pure white negative‑space cutout dominating the frame; minimalist poster style; scales of justice hologram balanced inside the zeros with a discreet courtroom wood texture behind the cutout; oxblood matte backdrop; high contrast, crisp edges, soft studio light, no other text, no logos
AGENTS md is a simple, open format for guiding coding agents. Works like a README but designed specifically for AI Agents to understand your codebase. Single file works across Cursor, Claude, OpenAI Codex, Google Jules, and Factory AI. https://x.com/Saboo_Shubham_/status/1957992746372985213
This is the word on the street I’ve been hearing in SF. Lots of people quietly prefer GPT-5 for code over Claude, counter to the memetic narrative on the TL”” / X https://x.com/BasedBeffJezos/status/1958942764747694593
Transforming human knowledge, sensors and actuators from human-first and human-legible to LLM-first and LLM-legible is a beautiful space with so much potential and so much can be done…
One example I’m obsessed with recently – for every textbook pdf/epub, there is a perfect “LLMification” of it intended not for human but for an LLM (though it is a non-trivial transformation that would need human in the loop involvement).
– All of the exposition is extracted into a markdown document, including all latex, styling (bold/italic), tables, lists, etc. All of the figures are extracted as images.
– All worked problems get extracted into SFT examples. Any referenced made to previous figures/tables/etc. are parsed and included.
– All practice problems are extracted into environment examples for RL. The correct answers are located in the answer key and attached. Any additional information is added as “answer key” for a potential LLM judge.
– Synthetic data expansion. For every specific problem, you can create an infinite problem generator, which emits problems of that type. For example, if a problem is “What is the angle between the hour and minute hands at 9am?” , you can imagine generalizing that to any arbitrary time and calculating answers using Python code, and possibly generating synthetic variations of the prompt text.
– All of the data above could be nicely indexed and embedded into a RAG database for later reference, or maybe MCP servers that make it available.
Then just as a (human) student could take a high school physics course, an LLM could take it in the exact same way. This would be a significantly richer source of legible, workable information for an LLM than just something like pdf-to-text (current prevailing practice), which simply asks the LLM to predict the textbook content top to bottom token by token (umm – lame). https://x.com/karpathy/status/1961128638725923119
ByteDance just opensourced a desktop automation AI Agent. This agent can use any desktop app, open files, and browse websites using vision models running locally. 100% Free, Opensource, and Local. https://x.com/unwind_ai_/status/1956538069311500514
AI Now Matches Prediction Markets in Forecasting Real Events, Study Finds https://finance.yahoo.com/news/ai-now-matches-prediction-markets-230346352.html
I built a small coding agent that lets you build high-quality agentic document workflows through natural language 🤖📑 Describe a reference document and the task you want to do over it (e.g. “split the document into each fund section, analyze the financials for each fund”) and https://x.com/jerryjliu0/status/1961123785597505603
We just raised a $14.5 million Series A led by @nexusvp to connect AI agents to the web Alongside it, we’re launching 2 big upgrades to @firecrawl_dev – our v2 API that supports faster scraping, news & image search and a brand new website The new chapter starts today 🔥 https://x.com/nickscamara_/status/1957824588970103193
A useful thing that GPT-5 can do that wasn’t previously possible before powerful AI is to monitor complex topics by asking it to give you scheduled reports. Example: I have a weekly report on “reproducible, benchmarked evidence of autonomous or recursive self‑improvement in AI” https://x.com/emollick/status/1959424313502961824
This is illustrative: 1) When you get an instant AI answer, it is from a small model, which are weak models, especially at math. 2) Non-reasoning models, like the one powering AI overview, only “think” as they write, they make mistakes & then back justify them as they write more.”” / X https://x.com/emollick/status/1959609082031063139
