Sam Flamini

Our Applied AI team with a great write up on improving Claude’s frontend design via Skills. Also with a Claude Code plugin that packages up the skill! claude.com/blog/improving…

it was awesome to work on this system, and I'm excited to share some of the things we learned! agents go brr

We finalized a new revision of MCP. Revision 2025-03-26 will bring Auth, Streamable HTTP, Audio modality and a few other goodies. We will be getting the SDKs up-to-date asap and will work towards a v 2.0 of the Python and Typescript SDK. But don't worry, everything is versioned so your existing MCP servers will work.

@aiDotEngineer @MaheshMurag @AnthropicAI Mahesh 👑

The highly-anticipated MCP workshop with @MaheshMurag is now live! Join @AnthropicAI Applied AI Engineer (+ creator of MCP) @MaheshMurag in this full 2-hour workshop covering the Model Context Protocol, where he covers: 00:00 Introduction 00:35 What is MCP? 09:39 Building with MCP 26:25 MCP & Agents 1:13:15 What's next for MCP? YT version in next post.

Some customers see upwards of 80% resolution rate, but on AVG we see 51% resolution rate. I think that's pretty incredible! I also want to give a special shout out to @PedroTabacof for leading the work on our end and @sflamini5 from Anthropic who has been excellent to work with.

@pratik60 @PedroTabacof Thank you Pratik! It's been a joy to work with you and the team

Excited to share our latest research on Contextual Retrieval - a technique that reduces incorrect chunk retrieval rates by up to 67%. When combined with prompt caching, it may be one of the best techniques there is for implementing retrieval in RAG apps. Let me explain:

Today was a special day to be @AssemblyAI 💙

Introducing Universal-1, our most powerful speech recognition model to date. Trained on over 12.5 million hours of multilingual audio data, Universal-1 achieves best-in-class speech-to-text accuracy across English, Spanish, French, and German. assemblyai.com/research/unive…

Underappreciated aspect of emerging AI market: Buying AI models is very different from buying SaaS -your purchase decision may impact COGS directly -pricing is based on usage, which you need to accurately forecast up front -technical evals more important than ever when buying

@naklecha @aaaaaaaaaaorg we both work in ai now sir

@sflamini5 @aaaaaaaaaaorg SAM how have you been

In January, I obsessively maxed out my "reading code, papers & math" skill tree. I'm excited to show off some of the stuff I've learnt, starting off with an (extremely detailed, hopefully useful) LLM blog dropping in late Feb :)

Almost every LLM eval system I've ever seen/built started with google sheets

Everyone wants to build smarter AI, but maybe the real opportunity is in using AI to create smarter humans

@thatguyintech this seems to be the path of most successful 'hard tech' founders

@sflamini5 win against competition first to earn the right to fight physics

Market risk vs technical risk Do you want to fight competition, or physics?

@thatguyintech Steak & eggs was my go to breakfast of choice in college

is it ok to eat steak between 6am - 10am

@thatguyintech @deformapp oh yes. will dm

@sflamini5 in the bay anytime soon? kinda want to explore this for @deformapp at some point

Technology often has such a high degree of specialization that going *just deep enough* into an area can quickly put you in the top 1% of domain knowledge in that space Many engineers dramatically underestimate the relative depth of their knowledge on their favorite topics

@thatguyintech integrating AI into products & business workflows

@sflamini5 whatchu going deep on these days?