Timing is impeccable, universe. @dwarkeshpodcast This is a blackboard episode that I’ll be watching on YT this long weekend. Though… I did listen to it while doing errands at home. Hello muxes. It’s been a min. Do we still get along? Did we ever get along? 😂 Ok it’s 2 AM.
Random side quest to catch up on the latest chip tech. Caveat: I haven’t done any chip design since 2009, so we’ll see if I even remember any VHDL/Verilog or FPGA/ASIC workflows. Against my better judgment, I’m gonna post my progress here, mostly for accountability.
🚨 #SXSW GIVEAWAY 🚨
TWO (2) SXSW FILM & TV BADGES
$2,790 TOTAL VALUE
1) Repost this
2) Follow us - @partywithdirty
3) Like this
That’s it. Winner (one winner gets both badges) announced 7pm Friday 2/21. Go!
.@GoogleColab will feature agentic coding capabilities using Gemini 2.0. Describe your data analysis goals, and watch your notebook take shape automatically. Get early access by joining the trusted tester program. https://t.co/gMl3K0mePY
Introducing the AI Engineer Pack.
Get $50+ in credits from each of the leading AI developer tools.
Whether you’re building a new AI product at work or launching a side project, the AI Engineer Pack has everything you need to build with AI.
The new Claude 3.5 Sonnet is the first frontier AI model to offer computer use in public beta.
While groundbreaking, computer use is still experimental—at times error-prone. We're releasing it early for feedback from developers.
Imagine listening to a lively discussion about your latest research project, summarized and analyzed by two AI hosts 🎧That's the power of #NotebookLM's Audio Overview. Upload PDFs, Google Docs, Slides, and try it for yourself.
✨Learn more at: https://t.co/JC66SQJxjh
SSI is building a straight shot to safe superintelligence.
We’ve raised $1B from NFDG, a16z, Sequoia, DST Global, and SV Angel.
We’re hiring: https://t.co/DmFWnrc1Kr
Understand papers via AI-generated discussions by Illuminate by @Google ? Yes please!! I create my own AI-generated Q&As for interview prep, so I love this experiment! Here's a link to the paper "Attention is All You Need" 😍 https://t.co/GCmoBdkRtW
Building a platform for generative AI applications
https://t.co/G9CFC6HLxt
After studying how companies deploy generative AI applications, I noticed many similarities in their platforms. This post outlines these common components, what they do, and implementation considerations.
This post starts from the simplest architecture and progressively adds more components.
1. Enhance context input into a model by giving the model access to external data sources and tools for information gathering.
2. Put in guardrails to protect your system and your users.
3. Add model router and gateway to support complex pipelines and add more security.
4. Optimize for latency and costs with cache.
5. Add complex logic and write actions to maximize your system’s capabilities.
I try my best to keep the architecture general, but certain applications might deviate. As always, feedback is appreciated!