• Link Archive - Mar 2025 • 03/2025
• Vibe Coding • 03/2025
• Thoughts on GPT-4o Image Generation • 03/2025
• Llama 3 Paper - Review (Part 2) • 03/2025
• Llama 3 Paper - Review (Part 1) • 03/2025
• Scaling Laws Paper - Review • 03/2025
• How to Become Irreplaceable • 03/2025
• Claude Code — Three Days In • 03/2025
• VQVAE – Review • 03/2025
• Claude Code • 03/2025
• Link Archive - Feb 2025 • 02/2025
• GAN – Review • 02/2025
• VAE – Review • 02/2025
• NeRF - Review • 02/2025
• DPO - Review • 02/2025
• RoFormer(RoPE) - Review • 02/2025
• Are You Smarter Than an LLM? • 02/2025
• Mamba - Review • 02/2025
• Structured State Spaces (S4) – Review • 02/2025
• Whisper – Review • 02/2025
• CLIP – Review • 02/2025
• Link Archive - Jan 2025 • 01/2025
• DeepSeekMath - Review • 01/2025
• DeepSeekMoE - Review • 01/2025
• DeepSeek-V2 - Review • 01/2025
• ViT - Review • 01/2025
• Samantha is here • 01/2025
• BERT - Review • 01/2025
• BLT – Review • 01/2025
• Continuous Latent Reasoning for LLMs (COCONUT) - Review • 01/2025
• Let's Reproduce GPT-2 by Karpathy - Review • 01/2025
• Transformer Circuits(Anthropic) - Review • 01/2025
• Karpathy's "Let's Build GPT From Scratch" - Review • 01/2025
• Curriculum learning for LLMs? • 01/2025
• Do LLMs Possess an Internal State of Mind? • 01/2025
• Advocating for OpenAI's for-profit model • 01/2025
• Link Archive - 2024 • 12/2024
• The Potential of an OpenAI Browser • 12/2024
• Generation vs. Verification: Epiphany after o1 • 09/2024
• From OpenAI to Anthropic Advocate • 08/2024
• Framing RLHF as Generation vs Verification • 08/2024
• Reflections on FSD and GPT-2 • 07/2024
• Data Quality in AI: Musings on LLMs and Synthetic Data • 07/2024
• The AI Conundrum: Human Mimicry vs. True General Intelligence • 07/2024
• The Alignment Problem • 03/2024
• Favorite Podcasts for 2023 • 01/2024
• Favorite Writings for 2023 • 01/2024