←
Yatharth5,065 posts
Yatharth avatar

Yatharth

@y99

when was the last time you did something for the first time? | failed founder 1x

◷ Joined January 2008▧ 580 Photos and videos
Yatharth avatar
Yatharth@y99·Oct 18

.. trained GPT-2 from scratch, kept all 32 checkpoints, and asked each “Who painted the Mona Lisa?” Step 0: gibberish Step 6k: “a very beautiful painting” Final: “Leonardo da Vinci… in the early 14th century” 😅 Built on @karpathy’s recipe. Ask yours: app.train.galvyn.xyz

Yatharth@y99Oct 18

When does a language model learn that water 💧 is a liquid I'm training GPT-2 (124M) live on one @nvidia RTX A5000 to learn. It's my 🏌️‍♂️ simulator :) Every step, watt and checkpoint is public, and you can talk to any checkpoint. app.train.galvyn.xyz/experim…

Post attachment
Mark Cuban avatar
⟳ Yatharth retweeted
Mark Cuban@mcuban·Nov 10

When you talked to Virginia Mason and UW Medical, curious what they said about how M4A would impact them and their care for residents of the state of Washington Can you share with us what they said ? Have you dynamically modeled the impact of M4A on leading Washington state hospitals and their patients ? Have you done any work on whether Direct Contracting is the way to go to reduce OOP costs for patients and employers ? Just trying to learn more. TIA !

For individuals buying their own private health insurance plans in Washington, premiums have increased by over 22% for 2027. This is outrageous and does not even include the potentially high deductibles, copays, or out-of-network costs. We need Medicare for All. seattletimes.com/business/en…

Yatharth avatar
Yatharth@y99·Nov 10

I thought I’d seen all the slack vs teams battles - but here is new one Use all of the above 🤯

Yatharth avatar
Yatharth@y99·Nov 5

Can I do a poll on @x but only US Senators and Congress accounts can reply :) ? Gets me direct answers

Yatharth avatar
Yatharth@y99·Nov 3

👀

NVIDIA Open-Sources Auto Ontology, a Semantic Layer for AI Agents Your boss asks the AI agent: "What was revenue last quarter?" It answers in 3 seconds. Clean number. Nice chart. But it used the wrong "revenue" column. 𝗡𝗼𝗯𝗼𝗱𝘆 𝗻𝗼𝘁𝗶𝗰𝗲𝘀. That's the problem NVIDIA's new open-source library, Auto Ontology, goes after. Its README puts it plainly: "…𝘢 𝘳𝘦𝘷𝘦𝘯𝘶𝘦 𝘮𝘦𝘵𝘳𝘪𝘤 𝘢𝘯𝘴𝘸𝘦𝘳𝘦𝘥 𝘧𝘢𝘴𝘵𝘦𝘳 𝘪𝘴 𝘸𝘰𝘳𝘵𝘩 𝘯𝘰𝘵𝘩𝘪𝘯𝘨 𝘪𝘧 𝘵𝘩𝘦 𝘯𝘶𝘮𝘣𝘦𝘳 𝘪𝘴 𝘸𝘳𝘰𝘯𝘨." 𝗪𝗵𝗮𝘁 𝗶𝘁 𝗶𝘀: A "context layer" that sits between an AI agent and your database. It tells the agent where the data lives, what each field means, and whether to use it. 𝗛𝗼𝘄 𝗶𝘁 𝘄𝗼𝗿𝗸𝘀, 𝘀𝘁𝗲𝗽 𝗯𝘆 𝘀𝘁𝗲𝗽: • 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿: it reads your database metadata and drafts an ontology, a map of business terms like "active customer" • 𝗚𝗿𝗼𝘂𝗻𝗱: agents use those terms instead of guessing from raw table names • 𝗩𝗮𝗹𝗶𝗱𝗮𝘁𝗲: it checks generated SQL against certified definitions • 𝗘𝘅𝗽𝗼𝘀𝗲: agents reach it through MCP, a CLI or an API • 𝗟𝗲𝗮𝗿𝗻: certified corrections go back into the map 𝗙𝗼𝗿 𝘂𝘀𝗲𝗿𝘀: Ask a question, get 𝘁𝗵𝗲 𝗮𝗻𝘀𝘄𝗲𝗿, 𝘁𝗵𝗲 𝗦𝗤𝗟 𝗶𝘁 𝗿𝗮𝗻, 𝗮𝗻𝗱 𝘁𝗵𝗲 𝗿𝗼𝘄𝘀. You can check the work, not just trust it. 𝗙𝗼𝗿 𝗯𝘂𝗶𝗹𝗱𝗲𝗿𝘀: • Apache 2.0, runs with Docker Compose or Helm • Works with Databricks, Postgres, Snowflake and DuckDB • Defaults to NVIDIA's Nemotron models, but 𝗮𝗻𝘆 𝗢𝗽𝗲𝗻𝗔𝗜-𝗰𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝗲𝗻𝗱𝗽𝗼𝗶𝗻𝘁 𝘄𝗼𝗿𝗸𝘀 • The MCP server has 𝟵 𝗿𝗲𝗮𝗱-𝗼𝗻𝗹𝘆 𝘁𝗼𝗼𝗹𝘀. There is deliberately no tool to browse raw tables, so agents must go through the business terms 𝗜𝘁 𝗯𝘂𝗶𝗹𝗱𝘀 𝗼𝗻 𝗲𝗮𝗿𝗹𝗶𝗲𝗿 𝘄𝗼𝗿𝗸: • Cube and dbt MetricFlow: semantic layers you write by hand in code • Wren AI: an open semantic layer for AI agents, with a context layer built partly by agents • Snowflake's Semantic View Autopilot: also drafts semantic models with AI, but only for Snowflake What's different here: 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲, 𝘄𝗼𝗿𝗸𝘀 𝗮𝗰𝗿𝗼𝘀𝘀 𝗳𝗼𝘂𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀, 𝗮𝗻𝗱 𝗯𝘂𝗶𝗹𝘁 𝗳𝗼𝗿 𝗮𝗴𝗲𝗻𝘁𝘀 𝘁𝗵𝗿𝗼𝘂𝗴𝗵 𝗠𝗖𝗣. 𝗧𝗵𝗲 𝗵𝗼𝗻𝗲𝘀𝘁 𝗽𝗮𝗿𝘁: • 𝗧𝗵𝗲 "𝟵𝟬% 𝗳𝗮𝘀𝘁𝗲𝗿" 𝗰𝗹𝗮𝗶𝗺 𝗶𝘀 𝗡𝗩𝗜𝗗𝗜𝗔'𝘀 𝗼𝘄𝗻 𝘁𝗲𝘀𝘁𝗶𝗻𝗴, with no baseline published • 𝗡𝗼 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆 𝘀𝗰𝗼𝗿𝗲𝘀 𝗮𝗿𝗲 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱. NVIDIA ships an eval harness (BIRD, 1,534 questions) but no results • That harness was tested with 𝗖𝗹𝗮𝘂𝗱𝗲 𝗢𝗽𝘂𝘀 𝟰.𝟴, 𝗻𝗼𝘁 𝗡𝗲𝗺𝗼𝘁𝗿𝗼𝗻 • 𝗪𝗶𝘁𝗵𝗼𝘂𝘁 𝗛𝗮𝘀𝗵𝗶𝗖𝗼𝗿𝗽 𝗩𝗮𝘂𝗹𝘁, 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 𝗽𝗮𝘀𝘀𝘄𝗼𝗿𝗱𝘀 𝗮𝗿𝗲 𝘀𝘁𝗼𝗿𝗲𝗱 𝘂𝗻𝗲𝗻𝗰𝗿𝘆𝗽𝘁𝗲𝗱 in Postgres (per the README) • It's young: 𝗮𝗯𝗼𝘂𝘁 𝟳𝟱𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀, and NVIDIA isn't accepting outside contributions 𝗧𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝗿 𝗽𝗼𝗶𝗻𝘁: the hard part of AI analytics isn't writing SQL. 𝗜𝘁'𝘀 𝗮𝗴𝗿𝗲𝗲𝗶𝗻𝗴 𝗼𝗻 𝘄𝗵𝗮𝘁 𝘁𝗵𝗲 𝘄𝗼𝗿𝗱𝘀 𝗺𝗲𝗮𝗻. GitHub: github.com/NVIDIA/auto-ontol… Links in reply 👇

Yatharth avatar
Yatharth@y99·Oct 28

🤯 | I guess maybe they should consider a poc :)

I don't think we should fight. The two companies are complementary. Since you're not doing this AI stuff, I really think Snowflake should consider getting its AI tokens through Databricks. You can get both cheap OSS models as well as frontier (OAI/Ant/Gemini/Grok) models from our platform. It all goes through Unity Gateway which has Smart Routing, Budgets, and Access Control. You can even use Omnigent with any harness, including CoCo. Most of our customers used this to reduce token spend ~30% last few months while token count went up. Genie lets you then track, control, manage that spend, all your financials, marketing, etc. Quick POC?

Yatharth avatar
Yatharth@y99·Oct 27

Does anyone have an recomendation for an @ElevenLabs setup with Claude or other but with some tool usage using adobe after effects or similar for text etc? Just ElevenLabs is very expensive

Yatharth avatar
Yatharth@y99·Oct 27

$10B idea AI Slop detector, not made by AI detector but look at slides/doc + content from meeting and detect AI slop vs value