Sabitlenmiş Tweet
Intelligence should be defined by the people closest to the work. Intelligence should be owned by all of us.
Let’s build a many model future!
Tuhin Srivastava@tuhinone
English
Baseten
2.3K posts
Baseten
@baseten
Inference is everything.
San Francisco and New York Katılım Mart 2021
344 Takip Edilen10.3K Takipçiler
Just came in the mail. Excited to read.
The book build & print quality is incredible!
Bravo @philipkiely & @baseten
English
I like what the @baseten team is doing. Asset light infra provider focused on best possible model deployments. Run fast, scale it simply and secure it everywhere. 👏
Amir Haghighat@amiruci
We now have a product specifically created for AI labs and their closed-weight models: we'll take care of not just inference, but auth, rate limits, metering, and billing integrations. We'll take care of providing both shared and dedicated inference, compliance needs, and matching end customers' geo requirements (us, ca, eu, uk, aus, jp, etc). It's called Baseten Frontier Gateway and is already battle-tested by multiple AI labs, like Poolside and their impressive Laguna M.1 agentic coding model.
English
@waterloo_intern this is almost as impressive as you getting the waterloo intern @
English
@matt_slotnick "hydrate them with inference" going immediately on our company water bottles
English
I have been saying this for a while.
It was only a matter of time until someone started running the much cheaper Chinese models on US-based infrastructure.
Until now, you could still argue:
"Who wants to send sensitive data to a Chinese provider?"
Healthcare, defense, government, finance - for many of them this was basically a no-go.
But if the same model runs on US-hosted hardware, with a US-based inference provider, many of those objections get weaker.
And then it gets interesting.
What happens when investors realize that maybe 50-70% of enterprise AI use cases don't need OpenAI or Anthropic at all?
Maybe they run fine on:
- cheaper hosted models
- open-weight models
- local models
- or some future box of GPUs nobody had on their bingo card
The big frontier models may still be needed for the hard stuff.
But if only 10-20% of workloads really need them, the ROI story looks very different.
That is where the card house starts to shake a bit.
English
Baseten retweetledi
Two years ago today I joined @baseten.
I don’t know how I got so lucky to work with such an incredible group of talented, driven, brilliant, genuinely wonderful people, but I feel grateful every day.
English
Baseten retweetledi
How do you handle the massive infrastructure demands of modern AI biology models? You bring in the inference experts.
Check out this clip from @benchling 's Mihir Trivedi and @baseten 's Bola Malek on why they teamed up to build Benchling Inference.
Dive into the full launch blog post: benchling.com/blog/announcin…
English
Baseten retweetledi
We’re launching Benchling Inference, powered by @baseten
It is scalable GPU capacity across 15 clouds for our 1300+ customers, preloaded with today's top scientific models and the integrations to make in silico discovery work out-of-the-box for biopharma companies.
Startups get better economics and availability. Enterprises get best-in-class infrastructure that works alongside their cloud commits and data sovereignty requirements.
It's been a pleasure working with Baseten on this. They've spent six years building at the leading edge of inference and are the compute behind some of the most demanding AI in production.
benchling.com/blog/announcin…
English
Biotech R&D is generating more scientific AI models than ever, from protein structure prediction to molecular docking to sequence analysis. But the infrastructure to run them hasn't kept up.
Today we're announcing Benchling Inference, powered by Baseten. Together with @benchling, we're delivering on-demand GPU capacity built for the bursty, high-stakes demands of scientific workloads. With Benchling Inference, scientists can:
→ Deploy models in seconds, not weeks
→ Keep proprietary models inside their VPC if needed
→ Benefit from economics that work even at small and mid-size biotech scale
Benchling and Baseten decided to team up because we believe that research teams shouldn't have to manage HPC queues, negotiate cloud contracts, or become GPU experts to run frontier models on their own data.
Six years of inference expertise are now available where science happens.
Read more here: benchling.com/blog/announcin…
English
“Intensity plus joy — an aha moment for me at Baseten is that those two things are not on opposite sides of a spectrum. Those can be inextricably linked, and that is the best.”
Our President @DannieHerz sat down with Conviction to chat GTM, culture, and hiring in an evolving AI market.
Niki Nguyen@niki4conviction
The pipeline of wisdom? Fully loaded. The close rate on great advice? 100%. I got a chance to sit down with the one and only @DannieHerz, president at @baseten, and talk all things GTM in this new era of AI. A few of my favorite takeaways: ✅ The AI-era sales hire is the tech enthusiast who uses the product, talks to engineers in their network, and earns trust by not sounding rehearsed. ✅ Culture = intensity + joy. Hire killers who are also a delight. ✅ Great recruiting isn't a pitch, it's relationship driven. No hard sell, just real work together with great people. Dannie joined Baseten for that exact reason.
English
Baseten retweetledi
Baseten retweetledi
I feel like we don’t talk about this enough: Baseten is hiring a ton.
Over 60 open roles (mainly SF and NYC, but we hire excellent people all over; Montreal, Miami, Toronto, Seattle, Boston…)
Everything here: baseten.co/resources/care…
English
English
Baseten retweetledi
working with @DannieHerz as an operator is a huge honor. she talks about what she's learned about building killer teams (especially GTM) in the AI-speed era, at @baseten @sequoia @SlackHQ @hubspot
Niki Nguyen@niki4conviction
The pipeline of wisdom? Fully loaded. The close rate on great advice? 100%. I got a chance to sit down with the one and only @DannieHerz, president at @baseten, and talk all things GTM in this new era of AI. A few of my favorite takeaways: ✅ The AI-era sales hire is the tech enthusiast who uses the product, talks to engineers in their network, and earns trust by not sounding rehearsed. ✅ Culture = intensity + joy. Hire killers who are also a delight. ✅ Great recruiting isn't a pitch, it's relationship driven. No hard sell, just real work together with great people. Dannie joined Baseten for that exact reason.
English
Sub-second image generation with Flux.2 [dev] and Qwen-Image:
Flux.2 [dev]: 2.3x faster, 0.98s latency (B200)
Qwen-Image: 1.6x faster, 0.87s latency (B200)
Details on how we got there in Faraz's article.
Faraz Shahsavan@Faraz9877
English
Last week, we launched Baseten Frontier Gateway. This week, Marylise sits down with Bola to talk about why.
Marylise Tauzia@marylise63530
I sat down with Bola, the brain behind our Baseten Frontier Gateway, to unpack why we built it, how we're already powering labs like Poolside, and where we're taking it next. If you're building a model lab, this one's for you. 00:00 Introductions 00:46 The Jagged Frontier Concept & Cambrian explosion of AI labs 03:34 The DeepSeek effect 06:06 What labs need to build a business & why existing gateways don’t work for inference 09:22 The gateway as a core infrastructure piece and what it actually does 11:44 Poolside as the launch partner for Baseten 13:42 What the gateway means for Baseten and closing message for labs founders
English
Baseten retweetledi
Great work at @baseten running vLLM-Omni in production — open-source, production-grade, cost-efficient omni-modal serving 🎙️
Multi-stage audio, streaming multi-modal, real-time TTS — workloads where closed-source APIs have been the default.
→ github.com/vllm-project/v…
Baseten@baseten
We serve Qwen3-TTS on vLLM-Omni at $3 per 1M characters. That's 90% lower in cost than comparable closed-source TTS APIs. Our engineers optimized a single-replica serving stack to get there. Details on the optimized stack and cost per concurrent stream here.
English
The work to make a clinical answer trustworthy includes figuring out which source applies, when the evidence is weak, and what the doctor is trying to decide. Charlie @oneill_c at @baseten on why AI companies train their own models. Must read.
Charlie O'Neill@oneill_c
English
Baseten retweetledi
Partnering with @baseten is a joy!
We love working alongside them to support the teams on the frontier.
Tuhin Srivastava@tuhinone
English