Taking a Citi Bike for a spin can be expensive. Recently, our @ Samantha Liebman took a 12-minute ride on a Citi Bike e-bike that resulted in a bill over $10. Now, some advocates are calling for a $3 cap on Citi Bike e-bike rides of 45 minutes or less for members.
Anthropic engineer:
"At Anthropic we don't write prompts anymore. We build loops and graphs."
In 30 minutes she shows how the Claude team builds systems that prompt themselves
Prompts → Agents → Loops → Graphs
a prompt gets you one answer
a loop gets the work done without you
a graph decides which work runs at all
if this cost $400 people would call it the best agents course of the year, and it is free
watch it today
then save the full graph engineering guide below before everyone catches up ↓
An extremely important functionality for agents is to simply extract fields out of PDFs. This turns out to be harder than people think because LLMs are primarily trained on predicting the next tokens. This leads them to "autocorrect" things that they shouldn't autocorrect. We launched an AI Extract capability that just excels at doing just this task with very high accuracy (95% vs 87% for others) and extremely low cost. Check out this blog on how we did it. The function can of course be called directly from SQL and be used throughout the platform.
https://t.co/60XC2mIZ2E
Today, we announced that we crossed $7B in revenue run-rate, growing over 80% year over year in Q2.
We also shared:
🚀 $100M+ revenue run-rate for Lakebase
🚀 $1.5B+ revenue run-rate for Lakehouse, growing over 100% year over year
🚀 Continued positive adjusted free cash flow
And we raised $5B in our latest fundraise.
We’ll use this capital to invest in:
1️⃣ Lakebase, our serverless Postgres database built for AI agents
2️⃣ Genie, our AI coworkers that actually understand your business data
3️⃣ Unity AI Gateway, our multi-AI governance solution that helps control costs
@iamVictorDey shares more in @Forbes:
https://t.co/y2LdxysBNi
Today @databricks we're publishing a detailed analysis of techniques we used to drastically reduce our internal AI spend while aggressively growing adoption. Savings come from layering in several techniques, which combine to drive unit costs down as much as 90% in some scenarios. Tl;dr, the wins come from:
1. Shifting defaults to more efficient models, including OSS models such as GLM. Maximum intelligence models simply aren't needed for many coding tasks, and "good enough" models are quickly becoming very cheap. We shift traffic between models using Unity AI Gateway. Approximate savings: 50% or more.
2. Using smart routing to automate model selection. Routing can further squeeze efficiency by dynamically selecting the model or harness that can most efficiently execute a particular task. Our task-level routing leverages @omnigent_ai. Approximate savings: 30%.
3. Providing user visibility and adaptive budgeting. Every user can see how much they spend, and users receive hints on how to contain spend. Heavy spenders encounter progressive friction as they ratchet spend above certain levels. Approximate savings: 10%.
4. Managing context bloat by pruning tool call results and tuning harness settings. Extraneous context costs $$ and delivers no value. Tuning cache settings also help lower average token costs. Approximate savings: 10%.
This is a BUSINESS ACCOUNT. I’ve been to Hell and back with this platform over the years and tried to stay off, but it just wasn’t feasible professionally. Having said that, do not try to TROLL or FUCK WITH ME on this page.