Glad this is up already!
A journal to keep track of your pet exercise, food and water intake and more!
Check it out: https://t.co/buOuBKxvM4
#iosdev#indiehacker#buildinpublic
@FloWritesCode This is something I’ve been actively avoiding to do. Localizing is such a pain that I fear it will slow down development 😅 so this looks definitely handy
You are 8 years old and you wake up on Christmas day. You see Pokémon Diamond under the tree. You stick all day playing in your pajamas. You are happy.
Damn, thanks a lot for the shoutout @Yosef_ktz, I appreciate it 🥹
About those suggestions you mentioned, I hear you loud and clear, hopefully coming in the following weeks with an update 👀
I was not able to keep track of monthly subscriptions 😢
I found this app made by @JosephSanchezC who created the most perfect and minimalist app to track all subscriptions ❤️
@subscribleapp Is a must download!!!!
I have a few suggestions for the app
- minimalistic widgets
- app icon for iOS 18 tinted icons
@JosephSanchezC Keep up your great work and I hope more people find out about this gem 🔥
Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet.
Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context window and improved support for 8 languages among other improvements. Llama 3.1 405B rivals leading closed source models on state-of-the-art capabilities across a range of tasks in general knowledge, steerability, math, tool use and multilingual translation.
The models are available to download now directly from Meta or @huggingface. With today’s release the ecosystem is also ready to go with 25+ partners rolling out our latest models — including @awscloud, @nvidia, @databricks, @groqinc, @dell, @azure and @googlecloud ready on day one.
More details in the full announcement ➡️ https://t.co/hhJoLm5eLV
Download Llama 3.1 models ➡️ https://t.co/rRjvmxqCTC
With these releases we’re setting the stage for unprecedented new opportunities and we can’t wait to see the innovation our newest models will unlock across all levels of the AI community.
💡📚 Understanding RAG and other concepts 📚💡
Retrieval is a deep topic, and there are many strategies to improve performance.
To help guide you, @RLanceMartin has completely revamped our retrieval docs! We now categorize key strategies for retrieval into seven different categories:
Query Translation: Reviewing/rewriting inputs
Routing: Mapping incoming queries to specific data sources
Query Construction: Taking advantage of the underlying structure of a database and metadata filters
Indexing: Ingest-time strategies to improve later performance
Search methods: Considering techniques beyond vector similarity search
Post-processing: Filtering, reranking, etc.
Generation: Self-correcting and sanity checking retrieved documents
We've also updated other parts of our conceptual docs to help you more deeply understand important ideas behind building with LLMs. Check it out below, and stay tuned for more!
🐍: https://t.co/3UCyr6BbyN
☕: https://t.co/Octkn8weZE
Coming soon, we’ll bring new multi-step reasoning capabilities to Google Search. It breaks your bigger question down into parts and figures out which problems to solve and in what order, so research that might've taken you minutes or even hours can be done in seconds. #GoogleIO