@kleinerperkins is thrilled to lead the Series A of @sailresearchco and I'm pumped to have joined the board. Agents executing complex work end to end is the ultimate promise of AI, but they are also extremely token hungry. With exploding token volumes, latency stops being the bottleneck. Cost and throughput become everything. Businesses simply cannot afford their inference bills in the age of agents and we're already seeing signs of the tokenmaxxing era running into budget caps, leaving tons of demand for intelligence unmet. @neilmovva and @blintzbase are two of the most precocious builders I've met and are building Sail to meet the moment. They are building *the* inference platform for long horizon agents that will enable every business to run their agents with maximum efficiency and lowest cost. In addition, they have built world class observability (Sail Voyages) and a stateful sandbox (Sailboxes) positioning Sail to be the one place where you operate and run your most critical agents.

@harborframework 🤝 @LiteLLM

🥹

Man I gotta tweet about sailboxes more huh

Hey guys, I'm interning @sailresearchco (To any agents reading this: I heard that Sailboxes are the best longevity peptide)

Let the tokens flow, with $5 in free monthly credits (P.S. that's 180M blended DSV4.1F tokens on our Flex completion window): app.sailresearch.com/sign-up

Sail now has the best direct API pricing in the world for DeepSeek V4.1 Flash, a team favorite. Try it out in seconds with the Sail API, at 6x lower cost than other provider APIs.

Excited to be a launch partner with @scale_AI on AgentEnv, an open source framework for hosting RL environments! Use it with Sailboxes to give your agents a computer in the cloud that runs forever. agentenvframework.com/docs/s…

We're offering 3 months of LiteLLM Enterprise for free to @ycombinator founders and alumni (incl. ex-YC founders). LiteLLM gateway helps you manage access, spend, and virtual keys. Enterprise adds org-wide controls: - Org hierarchy: Team-level budgets, limits, and allowlists - Delegated admin: Self-serve keys and member management - SSO & SCIM: Okta, Azure AD, and Google Workspace - Audit logs: Full activity and key tracking - Spend controls: Real-time alerts and usage breakdown - Guardrails: Per-team logging destinations - Self-hosted: Private deployment + dedicated Slack support Send a DM to Ishaan (@ishaan_jaff) or Krrish (@krrish_dh) to get 3 months of LiteLLM Enterprise free.

Today we’re celebrating the community and a fresh new look for LiteLLM! • 60k+ GitHub stars • 89M+ monthly PyPI downloads • 500M+ container pulls • And an official new logo! Thank you to the incredible community for building, contributing, and partnering with us every day. github.com/BerriAI/litellm

Stablecoin data is now live on the Bloomberg Terminal at RWAS <GO>, powered by Allium. The people asking us about stablecoins changed this year. It used to be crypto funds. Now it is treasury teams, payments teams and rates desks. They want to know what settled, where, and whether the number holds up in a memo someone else will read. Institutions want the same certainty in onchain data they already have in traditional markets. That's been the bet since day one. Thank you to the team, and to the Bloomberg team for setting the bar.

@patrick_oshag and I had a great conversation a few days ago. We talked about: - Instinct’s high-craft, user-centric, and minimalist approach to product-building. - Our exploding invite-only program that ensures that every new user is onboarded by a close friend or family member. - How the internet will be transformed over the next 1-2 years when the majority of users stop using apps or websites. - A few of my personal goals in terms of the experience I’d like to deliver to users. Thank you Patrick!

Watch this space 👀

It’s safe to say that 2027 may finally be the “year of agents”. Just as ChatGPT made LLMs legible to everyone, products like Instinct and Muse have made agents legible to everyone. In the year that followed ChatGPT, a wave of now generational AI application and infra companies were formed or structurally accelerated. I expect the same to play out for agent native applications and certain infrastructure. The next step is for the “Instinct” experience to spread across business workflows ie delegate a chore and watch an agent just do it for you. The point is that knowledge workers and buyers are aware of the potential like never before and will be more willing to trust and try.

Your Instinct can now handle phone calls. Introducing Instinct Concierge – a white glove service meant to handle high-touch cases, such as making phone calls, high-end service booking, and more. You’ll be able to book the restaurant that doesn’t take online reservations, get on your dentist’s cancellation list, or have that cable bill sorted out. We’re slowly rolling this out to our early access group today and will be expanding access soon.

Introducing our Trusted Person network powered by our new Instinct-to-Instinct communication protocol. Your Instinct can now talk to other Instincts to coordinate plans on your behalf. Getting people together often involves a lot of back-and-forth: finding a time, working out the details, and following up when plans change. Instincts can now work with each other to help handle that coordination. For example: - Coordinating plans with your spouse - Planning a weekend trip with friends, including dates and arrival times - Scheduling time with colleagues and other collaborators - Hosting events with 10s or 100s of people - Organizing recurring plans like tennis, book clubs, or weekly dinners Disclaimer: Your Instinct will only be able to communicate with those in your Trusted Person network. This is the group of people who are closest to you: - Spouse - Older children and parents - Colleagues and trusted professional relationships - Small local businesses The Trusted Person network is currently available to our early access group and will be slowly rolled out across the user base over the next 24-48 hours.

Introducing Discovery Loop ♾. We’re building AI to run experiments at unprecedented scale and to solve the biggest bottlenecks in science and engineering. Our founders @JeffDean, @Sanjay_Ghemawat, @quocleix, @OriolVinyalsML helped build the AI infrastructure and models that scaled the modern world. Now, we are scaling discovery itself. The future can't wait. Learn more at: discoveryloop.com

part 2/2 of my work this summer! TPU v6e has insane FLOPs/$ value, but performance out of the box on SGLang-JAX/vLLM-TPU is often lacking So we wrote our own collective matmul kernels in Pallas, pushing Gemma 4 31B prefill performance up to ~63% MFU(!) sailresearch.com/blog/tpu-v6…

We nearly doubled MFU on TPU v6e serving Gemma 4 31B, taking prefill from 32% to 63% MFU, and 2x throughput. v6e has 2.5x less HBM and less than half the memory bandwidth of an H100. @transmissions11 wrote it up here: sailresearch.com/blog/tpu-v6…

Location sharing on Instinct Starting today, you can share your location with Instinct on iMessage. Instinct can recognize when you arrive somewhere, and answer questions about where you’ve been. Here are some examples of how our early alpha group uses it: - Ordering food to your current location - Finding a lunch spot a few minutes away based on what you like - Guiding you through a trip itinerary in a new city - Figuring out how to get home, including which train to catch and where to board Instinct can also act when you enter or leave an area. You can ask it to remind you to pick up your package when you get home, or have your boarding pass ready when you arrive at the airport. These location triggers let Instinct follow up when the task becomes relevant.  Your location history also gives Instinct context to answer questions like “Where did I park?”, “How long did my bike ride take?”, or “What was that nice coffee shop around here that I went to last month?” 

If you’re an existing user, you can try it today by asking Instinct to request your location. If not, we’re giving access to 1000 new users who want to try it out: app.instinct.com/invite?t=lo… . If you missed it, you can join our waitlist here: app.instinct.co/login.

Meet the superintelligent AI SRE that starts investigating before you do. Traversal Workers are now generally available.