Sun, Nov 3, 2024

Weekly Notes and Discoveries | S Anand

Indian companies with 30+ employees MUST have 2.5%-15% of their employees as apprentices. Ref

The scientific discoveries that might have remained undiscovered for long if not for their discoverers Ref
- Newton's discovery of the universal law of gravitation
- Einstein's discovery of General Relativity
- McClintock's discovery of Transposable Elements: genes that can turn physical characteristics on and off
- Mullis' invention of the PCR that makes billions of DNA copies rapidly

structuredClone deep clones objects in JS #markdown

Rust has crazy low memory usage too. Spawning thousands of child processes is common and OK these days. Ref

SetInterval is a good idea in cyborg scraping. Ref #future

GH CLI is quite good for deployment too, like Wrangler CLI. Enabling pages, setting secrets, etc. #dev #github #prompt-engineering

Restic is a CLI backup tool. Just like git. Works well with rclone.

VibeCheck can predict a model based on its vibes 80% of the time. #future #prediction

/llms.txt is a proposal to standardize /llms.txt files as a way to share LLM prompts. #llm-ops #markdown
- Jina AI Meta Prompt is an example
- Remotion system prompt is an example
- https://docs.fastht.ml/llms-ctx.txt
- https://docs.fastht.ml/llms-ctx-full.txt

F5-TTS clones voices with just 15-second samples. #future #speech-to-text #tts #voice-cloning

NotebookLlama is an open source podcast generator like NotebookLM #llm-ops

Pragmatic Podcast (I forgot which one) #automation #code-agents #future #github #prompt-engineering
- Automate changelogs for your codebases. Convert past commits into attractive release notes automatically
- AI is going to be the consumer of many tools and logs. Build converters for these
- Speed of validation such as linting, testing, etc. will allow LLMs to iterate faster and WILL become more important

Via Soumya Ranjan #embeddings
- Vision embedding is useful in agile modeling
- Vision embedding models with SAM, Grounding Dino by meta, Alibaba does good stuff
- Vision embedding is more useful in batch than real time
- Embedding subtraction with vision embedding models like Dino

AI code editors are not good with large code bases today. Keep the refactoring exercises to below 1000 lines. Also evaluate the ease of setting it up locally #ai-coding #code-agents #github #markdown

Deepseek Janus is a 1.3b model that can generate both text AND images (and also supports vision) #image-generation

Cohere Multimodal Embed v3 is available on Azure. #cloud #embeddings

Elevenlabs lets you create voices with a prompt. No need to even clone one! #speech-to-text #tts #voice-cloning

Runway Act One creates expressive character performances #future