Machine Learning FLX @machinelearnflx

AI engineering, distilled. Agents, LLM systems, MLOps & infra architectures, papers, and tools worth your time. machinelearningflx.substack.com Italy Joined January 2016

Tweets

503K
Followers

171K
Following

28K
Likes

2K

Machine Learning FLX @machinelearnflx

14 hours ago

Try Build Apps and Fine-Tune LLMs Using the OpenAI API. Work through a practical chatbot example. aiflx.xyz/courses/build-… #AD #OpenAI

0 0 3 755 1

View Details

Machine Learning FLX @machinelearnflx

15 hours ago

Take a look at The Complete LangChain & LLMs Guide. Build an AI Research Assistant as a course project. aiflx.xyz/courses/the-co… #AD #LangChain

1 0 2 719 2

View Details

slash1s @slash1sol

2 days ago

This is f*cking insane. Chinese researchers just dropped a paper with a title that will make every agent framework nervous: "The End of Harness Engineering". The argument fits in one line: writing the program around the model is finished as a skill. A harness written by a human is one person's guess about one task on one afternoon. It ships, nobody re-reads it, nobody scores it, and the agent runs that guess for months. A harness written by the loop is a file that grades itself. A small 4B model reads what failed, writes 8 edits, and only the edit that scores best on held-out questions survives. The big model never changes. The file around it does, every round. So the human job collapses to one artifact: the scoring set. You write the questions, never the program. Frameworks turn disposable. The exam turns into the job. That is the exact loop I built and documented below: one harness.py, 300 Kimi K3 workers, 37 rewrites in 41 rounds, zero opened by me. The whole paper in one line: write the exam before the code ↓

slash1s @slash1sol

2 months ago

x.com/i/article/2092…

26 16 192 669K 424

76 156 1K 105K 2K

View Details

Machine Learning FLX @machinelearnflx

17 hours ago

Explore Fine-Tuning & Optimizing Large Language Models. Practice model adaptation with Hugging Face. aiflx.xyz/courses/fine-t… #AD #LLM

0 0 3 719 2

View Details

Machine Learning FLX @machinelearnflx

17 hours ago

Take a look at AI Agents with LangGraph, Semantic Kernel, and AutoGen. Learn to build multi-agent systems using AutoGen. aiflx.xyz/courses/ai-age… #AD #AIAgents #AutoGen

2 0 2 829 2

View Details

Archive @ArchiveExplorer

2 days ago

It is becoming f*cking dangerous: you can now reverse-engineer any repo with one command - a YC-backed tool with 127k stars maps the whole codebase, and your agent walks the map instead of reading files 1. Clone the project you want to understand 2. Install graphify: uv tool install graphifyy 3. Run graphify install (it detects Claude Code, Cursor, Codex or Gemini CLI) 4. Open the project and type /graphify . 5. Open graph.html: the architecture map nobody ever documented 6. Read GRAPH_REPORT.md: what everything flows through and the connections you didn't know were there 7. Ask: graphify path "A" "B" traces how two things connect, graphify explain shows everything one of them touches Code is mapped locally with no LLM, and every link says whether it was read or inferred Turn your agent into a reverse engineer that knows the whole project before it touches a single file Find the repo in the reply below

Archive @ArchiveExplorer

3 weeks ago

x.com/i/article/2101…

9 17 136 294K 320

33 112 858 140K 1K

View Details

Ricker @0xRicker

2 days ago

this is where REA × Kimi K3 starts to get dangerous. reverse engineering usually forces one model to keep too much of the app in context at once. REA changes the shape of the problem first. so the workflow becomes less like “read this codebase” and more like distributed forensics: map the surface → assign narrow investigations → trace relationships → compare findings → reconstruct the architecture the important part is that no single agent needs to understand the whole app. the swarm builds that understanding collectively. that’s what makes REA × K3 interesting to me: reverse engineering stops being limited by how much code one model can hold in its head. full course in the article below ↓

Ricker @0xRicker

5 days ago

x.com/i/article/2109…

11 15 155 103K 316

37 157 1K 48K 1K

View Details

Mr. Buzzoni @Mr_Buzzoni

2 days ago

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness the promise: > 200x faster > 400x cheaper the model hasn't been the slow part for a while the speed and the cost sit in the harness wrapped around it • how to use it > drop this PDF and the article below into Claude Code or Codex > let it rebuild its own setup one evening of setup and your agent starts next week on a harness most teams still don't have

Mr. Buzzoni @Mr_Buzzoni

3 weeks ago

x.com/i/article/2104…

17 53 464 1.0M 1K

22 134 1K 71K 2K

View Details

Alvaro Cintas @dr_cintas

2 days ago

Google just open-sourced its Harness² It's a plug-and-play framework for recursive agent harnessing in an open world. Agents can perform, and learn from, tasks its harness was never designed for. Built around 8 components: 1. System prompt 2. Guardrails 3. Memory 4. Tool guidance 5. Subagents 6. Skills 7. Scripts 8. Plugins Link: github.com/google-researc…

56 217 1K 79K 2K

View Details

ollama @ollama

2 days ago

✈ DeepSeek-V4.1-Flash-1017 is on Ollama! US-based hosting with zero data retention. It's strong on agentic tasks while being cheaper per task. Try it on Ollama Cloud: ollama run deepseek-v4.1-flash:1017-cloud Claude Code: ollama launch claude --model deepseek-v4.1-flash:1017-cloud OpenCode: ollama launch opencode --model deepseek-v4.1-flash:1017-cloud

DeepSeek @deepseek_ai

3 days ago

🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy,

2K 4K 37K 7.3M 7K

105 90 1K 143K 244

View Details

Machine Learning FLX @machinelearnflx

19 hours ago

Consider LLM Engineering with RAG: Optimizing AI Solutions. Get hands-on practice building AI applications with FAISS. aiflx.xyz/courses/llm-en… #AD #LLM #RAG

0 0 0 613 1

View Details

Machine Learning FLX @machinelearnflx

20 hours ago

Building AI Agents with OpenAI is worth a look. Deploy AI assistant systems with Streamlit. aiflx.xyz/courses/buildi… #AD #AIAgents #OpenAI

0 1 2 572 2

View Details

Machine Learning FLX @machinelearnflx

20 hours ago

Explore Generative AI Engineering with OpenAI API and AWS Models. Build RAG pipelines using Amazon Bedrock. aiflx.xyz/courses/genera… #AD #GenerativeAI #AWS

0 1 3 890 2

View Details

Machine Learning FLX @machinelearnflx

2 days ago

Try Project: Generative AI Applications with RAG and LangChain. Build a question-answering bot with a Gradio interface. aiflx.xyz/courses/projec… #AD #RAG #LangChain

0 0 0 900 0

View Details

Machine Learning FLX @machinelearnflx

2 days ago

On my radar: Responsible AI and the Law. Four standalone courses introduce non-lawyers to the intersection of AI and law. aiflx.xyz/courses/respon… #AD #ResponsibleAI #AILaw

0 0 0 674 0

View Details

Machine Learning FLX @machinelearnflx

2 days ago

Here's one to explore: DeepSeek in Practice. Learn to fine-tune DeepSeek models for applications such as legal reasoning. aiflx.xyz/courses/deepse… #AD #DeepSeek #AI

0 2 2 775 2

View Details

Machine Learning FLX @machinelearnflx

2 days ago

Take a look at IAPP AIGP Complete Training – AI Governance Mastery. Explore the NIST AI Risk Management Framework. aiflx.xyz/courses/iapp-a… #AD #AIGovernance #AIGP

0 0 2 803 0

View Details

Machine Learning FLX @machinelearnflx

2 days ago

Apply OpenCV for Real-Time Computer Vision Projects is worth a look. Build gesture-controlled applications with OpenCV and Python. aiflx.xyz/courses/apply-… #AD #OpenCV #ComputerVision