Baseten (@baseten) / X

How Parallel Web Systems pioneers programmatic web with high-throughput agentic inference

Jul 10

Agents will use the web more than humans ever have. High-accuracy AI web search is what @p0 is built for. We're proud to power the training and inference behind its Web Tool APIs, with 2x lower latency, 3x higher throughput, and 3x lower cost.

Quick stats: 3x higher throughput 2x lower latency 3x cost-savings vs. closed-source alternatives Company overview Parallel is built on a single premise: AI agents will use the web a thousand times...

How Parallel Web Systems pioneers programmatic web with high-throughput agentic inference

Quick stats: 3x higher throughput 2x lower latency 3x cost-savings vs. closed-source alternatives Company overview Parallel is built on a single premise: AI agents will use the web a thousand times...

Been working on this for a while - Built on Baseten is happening. August 4th, SF. Four early-stage founders getting on stage to share what they built and the infra decisions behind it More about them below 👇

Excited to be featured in Notion's newest customer story on how we're scaling expertise with Custom Agents! Meet katzgpt.

Notion

@NotionHQ

So @baseten runs billions of AI inference calls a day. And still hit a very human bottleneck: their first AE became the person with all the answers. Then answering became the job. So they built his digital double with Custom Agents. Questions that took Katz 30 minutes now take

00:00

The Digital Double: How Baseten Scaled Its Most-Asked Expert

Read the full story here:

EliseAI processes millions of conversations every month across housing and healthcare. We needed a critical voice agent feature to respond in under 1.3 sec. At anything slower, the conversation stops feeling natural and users stop engaging. We set out to build our own and

If you're at RAISE Paris today, come see @tuhinone on the master stage at 4:40 p.m. with @CorinneMRiley!

Thank you, @tbpn, for having our CEO @tuhinone on to talk about how companies of all sizes are investing in owning their intelligence with specialized, open-source models.

00:00

Watch the full interview here:

@baseten is building the inference infrastructure the AI era runs on. Proud to have @HSBCInnovation supporting their journey and it was great to sit down with @tuhinone and @DeepakBhandark8 to talk about it. If you're an AI founder or finance leader navigating this next phase,

00:00

We partnered with Braintrust to evaluate how GLM-5.2 performs on long-context retrieval tasks. Not only is its retrieval score effectively flat as context grows, but it's also over 4x cheaper than closed frontier models with comparable quality.

Braintrust

@braintrust

Jul 6

We built a Braintrust-native eval in collaboration with Baseten to test whether GLM-5.2 can preserve exact long-context retrieval under production serving constraints. GLM-5.2's retrieval score is effectively flat as context grows from 25K to 50K, which is the result users most

The future will be built on many models. Open-source: good enough for many use cases at a small fraction of the price. Specialized, post-trained: on par with, or better than generalist frontier quality for your specific use case, at a fraction of the price. Closed-source:

Lan

@ad0rnai

Jul 6

will open-source models become the majority of inference? @thdxr weighs in: YES

00:00

I went to Miami to chat with @thdxr, co-founder of OpenCode. We talked about the future of software engineering, coding agents, and why open source matters more now than ever. Timestamps: 0:00 Intro 5:30 Miami vs San Francisco tech scene 15:05 OpenCode origin story, scaling

00:00