Nisheeth Ranjan

We are entering an age of effortless creation. Yes, that means AI created content (including AI slop) will proliferate. But my hope is that human created digital content will also increase (assisted by tools that lower the friction of creation). I also hope that we end up creating more content (human or AI generated) that fosters human to human connection, understanding, and empathy.

@gauntletai @ashtilawat Ash's GitHub Repo: github.com/ashtilawat/min…

Just attended @gauntletai CTO @ashtilawat's awesome talk, "Building a Software Factory". Highly recommend you take a look at his Github repo (in reply below) and fork it to play with this idea. This factory concept can be applied to any digital creative endeavor, not just software. Talk online at: youtube.com/live/qsf45IblA…

New image gen model Uni-1 from @LumaLabsAI just dropped and it's architecturally interesting — autoregressive transformer that reasons through prompts BEFORE generating pixels. Beats Nano Banana on preference tests at 30% lower cost. Try it: app.lumalabs.ai Tech details: lumalabs.ai/uni-1 VentureBeat coverage: venturebeat.com/technology/lum…

Are you a software engineer interested in becoming an AI Engineer? Please read on. Do you know engineers who might like to become AI engineers? Please share this post. AI engineering skills are a key differentiator for all of us. I've started the "𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝘆" series of X posts with well defined milestones and live discussions to guide us on our journey towards becoming proficient AI engineers. 📌 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝘆, 𝗖𝗼𝗵𝗼𝗿𝘁 #𝟭, 𝗣𝗼𝘀𝘁 #𝟰 📌 𝗠𝗶𝗹𝗲𝘀𝘁𝗼𝗻𝗲 𝟰: 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 — 𝗙𝗿𝗼𝗺 𝗖𝗵𝗮𝘁𝗯𝗼𝘁𝘀 𝘁𝗼 𝗔𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗔𝗴𝗲𝗻𝘁𝘀 ✅ 𝗦𝘁𝗲𝗽 𝟭) 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 — 𝗪𝗵𝗮𝘁 𝗔𝗿𝗲 𝗔𝗴𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗪𝗵𝘆 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗠𝗮𝘁𝘁𝗲𝗿? Take Dr. Andrew Ng's "Agentic AI" short course on DeepLearning.AI. Learn agentic design patterns — reflection, tool use, planning, and multi-agent collaboration. ✅ 𝗦𝘁𝗲𝗽 𝟮) 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗮𝗻𝗱 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁𝘀: Read Anthropic's "Building Effective Agents" guide and their follow-up article "Effective Context Engineering for AI Agents". Build AI agents and feed them the right context (prompts, memory, tool outputs, etc.). ✅ 𝗦𝘁𝗲𝗽 𝟯) 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁𝘀: Read Anthropic's "Demystifying Evals for AI Agents". Build evaluation frameworks to measure and improve agent reliability. ✅ 𝗦𝘁𝗲𝗽 𝟰) 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 𝗶𝗻 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗲: Read Anthropic's case study on building their multi-agent research system. Learn how multiple specialized agents can coordinate on a complex task. ✅ 𝗦𝘁𝗲𝗽 𝟱) 𝗔𝗴𝗲𝗻𝘁 𝗣𝗿𝗼𝘁𝗼𝗰𝗼𝗹𝘀 — 𝗖𝗼𝗻𝗻𝗲𝗰𝘁𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁𝘀 𝘁𝗼 𝗧𝗼𝗼𝗹𝘀 𝗮𝗻𝗱 𝗘𝗮𝗰𝗵 𝗢𝘁𝗵𝗲𝗿: Read the intro to the Model Context Protocol (MCP) and take DeepLearning.AI's course on the Agent2Agent (A2A) protocol. MCP connects agents to tools; A2A connects agents to agents. Please do the above steps and reply below with questions and suggestions. 📌 𝗟𝗶𝘃𝗲 𝗔𝗠𝗔 𝘀𝗲𝘀𝘀𝗶𝗼𝗻 𝗼𝗻 𝗪𝗲𝗱𝗻𝗲𝘀𝗱𝗮𝘆, 𝗔𝗽𝗿𝗶𝗹 𝟴 𝗮𝘁 𝟵:𝟯𝟬 𝗮𝗺 𝗣𝗦𝗧 Please reply below to get the Zoom link to the live AMA session. Bring your questions, discuss progress and connect with peers. 📌 𝗟𝗶𝗻𝗸𝘀 (𝗳𝗼𝗿 𝘀𝘁𝗲𝗽𝘀 𝗮𝗯𝗼𝘃𝗲): 𝗦𝘁𝗲𝗽 𝟭 𝗟𝗶𝗻𝗸: learn.deeplearning.ai/courses/agenti… 𝗦𝘁𝗲𝗽 𝟮 𝗟𝗶𝗻𝗸𝘀: 1) anthropic.com/engineering/bu…, 2) anthropic.com/engineering/ef… 𝗦𝘁𝗲𝗽 𝟯 𝗟𝗶𝗻𝗸: anthropic.com/engineering/de… 𝗦𝘁𝗲𝗽 𝟰 𝗟𝗶𝗻𝗸: anthropic.com/engineering/mu… 𝗦𝘁𝗲𝗽 𝟱 𝗟𝗶𝗻𝗸𝘀: 1) modelcontextprotocol.io/docs/getting-s…, 2) learn.deeplearning.ai/courses/a2a-th…

Distributed pre-training of LLMs is getting better. Covenant is a 72B parameter model trained on 1.1T tokens via trustless peers on the internet. It scored 67.4 on the MMLU benchmark beating LLaMa-2-70B (released 3 years ago) which got 63.1 and was trained on ~2T tokens. arxiv.org/abs/2603.08163

Last week my goal for 2026 was to build a revenue positive self operating business run by up to 10 autonomous agents. Earlier today I saw Kelly AI: an agent managing an idea factory, a software factory for iOS apps, and a marketing factory generating revenue from day 1. Looks like I need to aim higher! 😀

One thing I’m thinking about is how much we create vs consume using human or artificial intelligence. I think all knowledge workers can measure and increase their creation-consumption ratio (CCR) by leveraging AI to create software, text, music, audio, images and video. Creation is active whereas most consumption is passive so a higher CCR directly correlates to higher human agency and more bias to action. Optimizing CCR is critical in the AI age.

All knowledge workers can 10x amplify what they love to do *and* 10x reduce what they don’t like to do by leveraging AI. If you are a knowledge worker and not already doing this, figure out a path to do this in 2026. All the tools and technology to enable this is getting better by the day.

Reading Accelerando, written in 2005, feels surreal. The author (Charles Stross) got so many things right, it feels like he time-travelled into the future before writing the book. If you want to prepare for the Singularity, read it: bookshop.org/p/books/accele…

This is a really interesting development: a software factory: factory.strongdm.ai. @strongdm says: - Code must not be written by humans - Code must not be reviewed by humans - If you haven't spent at least $1,000 on tokens today per human engineer, your software factory has room for improvement I’m not sure if I’m ready for $1000/eng/day spend but I’m intrigued by the factory idea where no code is written or read by humans. The article links to @strongdm principles, techniques, and products that relate to how they built their software factory. Definitely worth exploring further.

I have now run the Ralph loop in plan mode and in build mode (see github.com/nisheeth/ralph…) and am loving the results. I hit my Claude Max usage limit once already. Next goal is to consistently run the loop to plan/build and hit the usage limit daily. Not there yet.

@GeoffreyHuntley @ClaytonFarr Here's the Ralph Loop github repo: github.com/nisheeth/ralph…

Running a 4 spec Ralph loop today to work on my family legacy platform: ourlegacy.family. Hat tip to @GeoffreyHuntley for his videos/blogs on Ralph loops and @ClaytonFarr for his GitHub repo that I just forked.

Are you a software engineer interested in becoming an AI Engineer? Please read on. Do you know engineers who might like to become AI engineers? Please share this post. AI engineering skills are a key differentiator for all of us. I've started the “𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝘆” series of LinkedIn posts with well defined milestones and live discussions to guide us on our journey towards becoming proficient AI engineers. 📌 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝘆, 𝗖𝗼𝗵𝗼𝗿𝘁 #𝟭, 𝗣𝗼𝘀𝘁 #3 📌 𝗠𝗶𝗹𝗲𝘀𝘁𝗼𝗻𝗲 𝟯: 𝗛𝗼𝘄 𝘁𝗼 𝗠𝗮𝗸𝗲 𝗮 𝗖𝗵𝗮𝘁𝗯𝗼𝘁 ✅ 𝗦𝘁𝗲𝗽 𝟭) 𝗢𝘃𝗲𝗿𝘃𝗶𝗲𝘄: Watch Andrej Karpathy's video, "Deep Dive into LLMs like ChatGPT", which covers all the steps that go into making a modern chatbot like ChatGPT. ✅ 𝗦𝘁𝗲𝗽 𝟮) 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱 𝘁𝗵𝗲 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿 𝗡𝗲𝘁𝘄𝗼𝗿𝗸 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲: Read Jay Alammar's "The Illustrated Transformer" blog post that visually explains the Transformer neural network architecture. Optional: Read "The Annotated Transformer" blog post. It is also a working notebook so run the code as you read it. It is an annotated version of the famous "Attention is All you Need" paper in the form of a line-by-line implementation. ✅ 𝗦𝘁𝗲𝗽 𝟯) 𝗣𝗿𝗲-𝘁𝗿𝗮𝗶𝗻 𝘁𝗼 𝗴𝗲𝘁 𝗮 𝗯𝗮𝘀𝗲 𝗺𝗼𝗱𝗲𝗹, 𝗣𝗼𝘀𝘁-𝘁𝗿𝗮𝗶𝗻 𝘃𝗶𝗮 𝗦𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗙𝗶𝗻𝗲 𝗧𝘂𝗻𝗶𝗻𝗴 (𝗦𝗙𝗧) 𝗮𝗻𝗱 𝗥𝗲𝗶𝗻𝗳𝗼𝗿𝗰𝗲𝗺𝗲𝗻𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗛𝘂𝗺𝗮𝗻 𝗙𝗲𝗲𝗱𝗯𝗮𝗰𝗸 (𝗥𝗟𝗛𝗙) 𝘁𝗼 𝗴𝗲𝘁 𝗮 𝗰𝗵𝗮𝘁𝗯𝗼𝘁 𝗮𝗹𝗶𝗴𝗻𝗲𝗱 𝘄𝗶𝘁𝗵 𝗵𝘂𝗺𝗮𝗻 𝗽𝗿𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲𝘀: Read Sebastian Raschka's "LLM Training: RLHF and its Alternatives" blog post. Read and watch the video on Oxen.ai's "Training Language Models to Follow Instructions (InstructGPT)" blog post. Optional: Read the March 2022 research paper "Training language models to follow instructions with human feedback". Please do the above steps and reply below with questions and suggestions. 📌 𝗟𝗶𝘃𝗲 𝗔𝗠𝗔 𝘀𝗲𝘀𝘀𝗶𝗼𝗻 𝗼𝗻 𝗪𝗲𝗱𝗻𝗲𝘀𝗱𝗮𝘆, 𝗢𝗰𝘁𝗼𝗯𝗲𝗿 𝟭𝟱 𝗮𝘁 𝟵:𝟯𝟬 𝗮𝗺 𝗣𝗦𝗧 Please reply below to get the Zoom link to the live AMA session. Bring your questions, discuss progress and connect with peers. 📌 𝗟𝗶𝗻𝗸𝘀 (𝗳𝗼𝗿 𝘀𝘁𝗲𝗽𝘀 𝗮𝗯𝗼𝘃𝗲): 𝗦𝘁𝗲𝗽 𝟭 𝗟𝗶𝗻𝗸: youtube.com/watch?v=7xTGNN… 𝗦𝘁𝗲𝗽 𝟮 𝗟𝗶𝗻𝗸𝘀: jalammar.github.io/illustrated-tr…, 𝗢𝗽𝘁𝗶𝗼𝗻𝗮𝗹 𝗟𝗶𝗻𝗸: nlp.seas.harvard.edu/annotated-tran… 𝗦𝘁𝗲𝗽 𝟯 𝗟𝗶𝗻𝗸𝘀: 1) magazine.sebastianraschka.com/p/llm-training…, 2) oxen.ai/blog/training-…, 𝗢𝗽𝘁𝗶𝗼𝗻𝗮𝗹 𝗟𝗶𝗻𝗸: arxiv.org/pdf/2203.02155

Would you use Eva AI (youreva.org), an AI powered secretary that helps you stay focused and feel less overwhelmed? Eva AI works 24/7 in the background, constantly learning and optimizing your life. It understands what you see, hear, and do. It treats your privacy as sacred. It monitors your meditation, sleep, diet, and exercise. It takes your directions and performs actions on your behalf. It plans and prioritizes your day allowing you to focus completely on the present moment. It is proactive and gives you insights and suggestions based on everything it knows about you. Does the above resonate? If so, please sign up on the waitlist at youreva.org. #AI #Secretary #Health #Assistant #Holistic

Are you a software engineer interested in becoming an AI Engineer? Please read on. Do you know engineers who might like to become AI engineers? Please share this post. AI engineering skills are a key differentiator and productivity enhancer for all of us. I've started the “𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝘆” series of posts with well defined milestones and live discussions to guide us on our journey towards becoming proficient AI engineers. 📌 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗔𝗰𝗮𝗱𝗲𝗺𝘆, 𝗖𝗼𝗵𝗼𝗿𝘁 #𝟭, 𝗣𝗼𝘀𝘁 #𝟮 📌 𝗠𝗶𝗹𝗲𝘀𝘁𝗼𝗻𝗲 𝟮: 𝗣𝗿𝗼𝗺𝗽𝘁 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴, 𝗥𝗔𝗚, 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀 ✅ 𝗦𝘁𝗲𝗽 𝟭) 𝗣𝗿𝗼𝗺𝗽𝘁 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴: Read and/or watch the videos on "The Prompt Report Parts 1 and 2" blog posts from Oxen.ai and read OpenAI's guidelines for text generation and prompting. Optional: Read the June 2024 research paper ("The Prompt Report: A Systematic Survey of Prompt Engineering Techniques"). ✅ 𝗦𝘁𝗲𝗽 𝟮) 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗲𝗱 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 (𝗥𝗔𝗚): Read LangChain's overview on RAG, implement LangChain's tutorial on building a search engine over a PDF document, and read Cameron Wolfe's "Practitioner's Guide to RAG" blog post. Optional: Read the May 2020 research paper ("RAG for Knowledge-Intensive NLP Tasks"). ✅ 𝗦𝘁𝗲𝗽 𝟯) 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻: Read "RAG Evaluation Metrics Explained: A Complete Guide" blog post and read and/or watch the video on Oxen.ai's "RAGAS - Retrieval Augmented Generation Assessment" blog post. Optional: Read the Sep 2023 research paper ("RAGAS: Automated Evaluation of RAG") and the May 2024 research paper ("Evaluation of RAG: a Survey"). Please do the above steps and comment below with questions, suggestions, and links to your creations. 📌 𝗟𝗶𝘃𝗲 𝗔𝗠𝗔 𝘀𝗲𝘀𝘀𝗶𝗼𝗻 𝗼𝗻 𝗪𝗲𝗱𝗻𝗲𝘀𝗱𝗮𝘆, 𝗝𝘂𝗹𝘆 𝟭𝟲 𝗮𝘁 𝟵:𝟯𝟬 𝗮𝗺 𝗣𝗦𝗧 Please reply below or DM me to get the Zoom link to the live AMA session. Bring your questions, discuss progress and connect with peers. 📌 𝗟𝗶𝗻𝗸𝘀 (𝗳𝗼𝗿 𝘀𝘁𝗲𝗽𝘀 𝗮𝗯𝗼𝘃𝗲): 𝗦𝘁𝗲𝗽 𝟭 𝗟𝗶𝗻𝗸𝘀: 1) oxen.ai/blog/the-promp…, 2) ghost.oxen.ai/the-prompt-rep…, 3) platform.openai.com/docs/guides/te…, 𝗢𝗽𝘁𝗶𝗼𝗻𝗮𝗹 𝗟𝗶𝗻𝗸: arxiv.org/abs/2406.06608 𝗦𝘁𝗲𝗽 𝟮 𝗟𝗶𝗻𝗸𝘀: 1) python.langchain.com/docs/concepts/…, 2) python.langchain.com/docs/tutorials…, 3) cameronrwolfe.substack.com/p/a-practition…, 𝗢𝗽𝘁𝗶𝗼𝗻𝗮𝗹 𝗟𝗶𝗻𝗸: arxiv.org/abs/2005.11401 𝗦𝘁𝗲𝗽 𝟯 𝗟𝗶𝗻𝗸𝘀: 1) @med.el.harchaoui/rag-evaluation-metrics-explained-a-complete-guide-dbd7a3b571a8" target="_blank" rel="nofollow noopener">medium.com/@med.el.harcha…, 2) ghost.oxen.ai/arxiv-dive-rag…, 𝗢𝗽𝘁𝗶𝗼𝗻𝗮𝗹 𝗟𝗶𝗻𝗸𝘀: 1) arxiv.org/abs/2309.15217, 2) arxiv.org/abs/2405.07437 #AIEngineerAcademy #AI #CareerGrowth #MachineLearning #SoftwareEngineering