Llama 4
eli5b: explain like i'm 5b
Llama 4 launched on May 20, 2025 with 12 votes, #1,538 of 7,905 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Explain Like I'm 5B. Improving communication between large languge models and small language models. A project done for the Stanford 8VC + Meta Llama Hackathon.
Explain Like I'm 5B. Contribute to victorkolev/eli5b development by creating an account on GitHub.
Explain Like I'm 5B. Improving communication between large languge models and small language models. A project done for the Stanford 8VC + Meta Llama Hackathon. Work done by Jubayer Ibn Hamid, Ifdita Hasan Orney, and Victor Kolev. Agentic systems involve multiple models interacting with each other. Often this takes the form of a large "System 2" LLM instructing a smaller, task-specific "System 1" L(S)LM. For example, many SWE agents hand off repo exploration to a small models for better efficiency; in robotics, VLA models are often small so that they can be fast for high-frequency control. However, models have been instruction-tuned based on instructions by humans. We hypothesize that the…from github.com
Does a similar job
all alternatives →
Llama 3.3 70B2024 · developer.meta.com · ▲347Llama 405B-level performance, at a fraction of the cost
I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Llama 3.2 Interpretability with Sparse Autoencoders2024 · github.com · ▲579I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2025
the whole month →
Tapflow 2.0▲1,125We built Tapflow for devs, designers, PMs, and tech folks who’ve been sitting on internal docs, templates, and systems — but never productized them. Upload a PDF, notes, or workshop deck, and Tapflow drafts a structured product (with chapters, teaser and pricing plans). It’s good for AI kits, onboarding guides, design systems, and frameworks. You can sell through Stripe, LemonSqueezy, or PayPal. Real-time collaboration is in early beta. No site builder, no LMS — clean design and just focused tools to ship. Fully bootstrapped and just launched on PH today →…
Work · 2025 · tapflow.ai
- C9
Life & fun · 2025 · felixrieseberg.github.io
Appwrite Sites▲990Appwrite 2.0 brings a new engine, a rebuilt Console, five database types, an S3 API, an OAuth 2.1 server, and organization-level Domains and Firewall.
Dev tools · 2025 · appwrite.io
