Took @VictorTaelin’s awesome experiments around compressing GPT prompts and built CompressGPT. A one-line change in your @LangChainAI code => 70% token usage deduction! https://t.co/P3wuFEb2P2

we migrated from langsmith to logfire and the time it took to query our agent traces went down by 96.2%

Working with the next household name in this list (currently ~Series B stage), where a staggering ~1/3 of the team is former founders. They are hiring! Message me for details.

Really excited to announce Root Ventures Fund 4, our new $190M seed fund supporting technical founders working on hard problems with up to $5M at any stage with “seed” in the title. We are so grateful to @EricNewcomer for perfectly capturing our vibe in his article below: 👇

We have a new coffee grinder (and $190M fund). I rebuilt the electronics to add grind-by-weight and Wifi/BLE. The firmware is also running a server to announce our new fund: https://t.co/J7fiXQ10ZS ☕️🚀🤑

since ppl keep tagging me - it's clear the market has a latent desire for this "future slack." it's a tough problem bc it won’t look like anything we have today we're working hard, iterating patiently, and are constantly looking for the right ppl to join Ando. DM if you're eager

We're growing the team! 📍 NYC 🧠 Roles: Research Engineer, Founding Solutions Engineer 🔗 https://t.co/VSSj65go0K You: want to build and scale SoTA infrastructure loved by 50k+ developers and trusted by tier 1 research labs, Fortune 100s, and hyper-growth startups Us:

Introducing Stream & Stream Ring. Let thoughts & ideas flow ∽ Preorder now at https://t.co/ORVXv7ZOLL

anyone building something similar to @agentmail / @resend's inbound feature?

We're excited to collaborate with @datalabto to make high-throughput document intelligence accessible to all developers. Instantly deploy and scale Datalab's best-in-class Marker pipeline on Modal GPUs 📑

easiest money i've ever made

I'm teaming up with @samuel_colvin to launch a new meetup series, Py AI. Our first one is November 11 in San Francisco with talks from @pydantic, @modal, @reductoai and @fastmcp. Hosted by our friends at @pebble_bed. Link to join below!

Kind of mad seeing AMD using @pydantic Logfire to demo the performance of open models on their hardware at Pytorch today. The future is Pydantic.

You have to try https://t.co/Ho09ulo3vQ to really experience how fast this is. (Also, the playground is running on @modal 🙂)

Just putting this here. Not much more to say. @pydantic

For as long as humans have had children, we’ve hoped and prayed they’d be healthy. For the first time in history, we can do more than hope. @OrchidInc gives parents knowledge before life begins… a chance to build the healthiest future possible. Fast Company just told our

We've raised our Series B! We’re excited to grow our team and continue building AI-native infrastructure to power the next generation of applications. Thank you to our investors, the Modal team, and our community 💚 https://t.co/ATzEhhdE9f

The best part about working on @modal is watching our customers literally build the future. Today, they’re using @modal for everything from generating AI music to powering real-world robots to curing cancer. And yet, this is just the beginning. We have so much more to build.

Will you have an average baby or a superbaby? Last week in SF, we threw a party to celebrate the first generation of @OrchidInc superbabies (real children whose parents gave them the healthiest possible start by screening their DNA as embryos!) Then we sat down to record a

. @ekzhang1 and team have spent the last 8 months building the best ML experimentation and collaboration experience in the browser. Go try it now at https://t.co/Jr8JwbTTW3.

talked to another great team today who ripped out their ai framework the story is the same every time -- most of the value of an abstraction is abstracting across LLMs the rest eventually weighs you down