- Big Data News Weekly
- Posts
- 🤖 Using Scikit-LLM with Open-Source LLMs
🤖 Using Scikit-LLM with Open-Source LLMs
🦾Plus: 🏛️ Washington eyes an ownership slice of OpenAI
In partnership with
Hey folks! Let’s get into Big Data and AI craziness…
In today's edition: Key stories for data teams and AI builders 👇
🔧10 Open-Source Libraries for Fine-Tuning LLMs
🧪 Claude Opus 4.7 Beat Specialist Chemistry Software
📉 DeepSWE Benchmark Exposes the True Gap in Coding Models
🤖How to build and deploy a Slack AI agent
🚀 OpenAI’s ‘superapp’ revamp is coming soon
💡 AI Tutorial: Repurpose long videos into shorts in one click
🤖AI Tools and Data Tools to checkout
In this article, you will learn how to use locally hosted language models through Ollama to perform text classification tasks, all without spending a cent on API calls. Topics we will cover include: How to install Ollama and pull open-source models like Llama 3, Mistral, and Gemma to run locally on your machine. How to configure the Scikit-LLM library to route requests to a local Ollama endpoint instead of a paid cloud API.
The GTM bets that shouldn't have worked, and did
One grew revenue 50x after half his team quit over the strategy. One brought in 50K signups in a single day with no paid budget. One generated 100M+ views from a stunt that took 50 hours to conceive. One asked every prospect to demo the product themselves instead of demoing it for them.
None of them followed the safe playbook. They treated GTM like an experiment, moved before they had proof, and made bets most founders would never get approved.
HubSpot for Startups documented all 6 stories in the free Bold Bets Playbook. The risks they took, why it was risky, and what it returned.
10 open-source libraries changed this by rewriting how training happens. Custom kernels, smarter memory management, and efficient algorithms make it possible to fine-tune frontier models on consumer GPUs.
If you aren't familiar, NMR software is the gold-standard expert tool chemists use to turn molecular structures into predicted lab spectra. It’s highly specialized, highly technical stuff. But Opus 4.7 completely disrupted the workflow! It matches the specialists: Opus 4.7 produced the smallest hydrogen prediction errors. It’s predicting NMR signals just as well as the tools built explicitly for this one job.
Datacurve just dropped DeepSWE, a new long-horizon software engineering test designed to show where leading AI models truly separate. The results are a massive reality check. On this new benchmark, GPT-5.5 hits just 70%. GPT-5.4 comes in at 56%, and Claude Opus 4.7 sits at 54%.
You'll learn how to build and deploy an AI Slack bot from scratch using Node.js, OpenAI, and LangChain. This tutorial covers everything from automating community research and using GPT-4 to calculate user fit scores to integrating a PostgreSQL database and pushing your production-ready agent live on Render.
Some Work Requires You. Most of It Doesn’t.
Some work needs your leadership. Most just needs to get done.
When everything lands on your plate, that line disappears and your time gets consumed by work that shouldn’t be yours.
The Freedom Framework shows you what to keep and what to confidently hand off so you can focus on what truly moves your business forward.
👨💻 Data Tools, Libraries
Open Code Review (GitHub Repo)
Open Code Review is an AI-powered code review CLI tool that reads git gives, sends challenged files to a configurable LLM via an agent with tool-use capabilities, and generates structured review comments with line-level precision.
kysely
A type-safe typescript SQL query builder.
GraphGPT
Extrapolating knowledge graphs from unstructured text using GPT-3.
Sintra: The AI "dream team" for overwhelmed operators. Access 12+ specialized agents that handle marketing, sales, ops, and much more for you - no prompting experience required.
AI News:
OpenAI is reportedly planning its biggest ChatGPT revamp yet “in the coming weeks”, which will rebuild ChatGPT into an agent-and-coding "superapp" that prioritizes pushing its nearly 1B users toward paid products ahead of its upcoming IPO. The reorganization will place greater focus on its agentic coding platform, Codex, with a senior OAI member telling the Financial Times that “Chat is dead”.
Claude is not just a chatbot anymore. Is your security team ready?
Claude.ai is one thing. Agentic workflows, MCP connections, ungoverned skills taking actions across your data? That's a different conversation — and most security teams aren't equipped for it.
Harmonic Security gives your CISO the visibility and controls to say yes confidently.
One of the first engineers on OpenAI's chip program just left for Anthropic. Clive Chan, one of OpenAI's first custom chip hires, has joined Anthropic after about 2.4 years. His old team built the silicon effort behind OpenAI's 10 gigawatt Broadcom deal. Anthropic currently runs Claude on Google TPUs and Amazon chips, but reportedly began weighing its own custom silicon around April.
The White House and OpenAI are reportedly in talks over the U.S. government taking an equity stake in the company, with the shares potentially going towards a "Public Wealth Fund" built to hand Americans a cut of the AI boom. Axios reported that industry backers have discussed a 1-5% stake, far below U.S. Senator Bernie Sanders' proposed one-time 50% stock tax on AI labs.
An optional security setting that disables web browsing, deep research, and agent mode to protect people handling sensitive data from prompt-injection attacks.
Facebook has long been filled with feeds of clickbait articles. Now, Meta is making its own clickbait articles with AI. The standalone Meta AI app now has a “For You” section that populates a list of clickbait-style stories for you to read. But the topics, images, and text are all AI-generated — and as questionable as you’d expect from AI-created works.
Ultimate AI Tool Kit is a massive guide that covers everything you need to know about Artificial Intelligence, AI Tools and ChatGPT. It is designed for those who want to be more than just an average person when it comes to AI and ChatGPT, GPTs.️
AI Tutorial
Repurpose long videos into shorts in one click
Go to OpusClip and sign up.
Enter the URL or upload your video.
Click on "Get clips in 1 click," and wait a few minutes for AI to do all the work.
You can select "Edit clip" to make changes as needed.
Once done, download or share the clip on social media.
If you’ve ever stared at your screen wondering where the real opportunities are hiding, this class is your shortcut.
In this free live session from VantagePoint, you’ll see how modern A.I. cuts through the noise and zeroes in on the sectors, stocks, and setups that actually matter right now. No guessing. No chasing. Just clear direction based on intermarket signals that most traders never even realize are moving their trades.
If the markets feel chaotic, this is where you regain control. Sign up now for your free live training with VantagePoint.
🔥Top AI tools to increase productivity:
AirRankPilot helps local businesses get discovered by Google and AI tools like ChatGPT and Perplexity
InboxKit is your all-in-one platform for building, managing, and scaling cold-email infrastructure.
CCPayment is a cryptocurrency payment platform allowing merchants to accept and payouts
HuePress is a SaaS platform providing therapy-grade, high-quality printable coloring pages
Creatives Takeover is an AI platform that turns raw founder ideas into business plans
Pixel‑exact AI image generator composing scenes on fixed canvases
Reelbase - Create Viral TikTok Slideshows in Seconds
Qeeebo is an AI-curated question-and-answer platform built with a clear and ambitious purpose
View our database of all the best AI tools for your needs: aitoolsup.com
Have cool resources to share? Submit AI tool
A.I. Generated Image of the Day
👀 Medusa gives Rapunzel a hair makeover
Recommended reading:
SPONSOR US
Get your product in front of Big Data & AI enthusiasts
😮 The Marketing Channel You've Probably Slept On:
Haven't tried newsletter sponsorships yet? You are missing out on a HUGE ROI+ customer acquisition channel. I know because dozens of advertisers keep coming back for more... Run a test campaign with us and see for yourself 👉 Get in touch today.
What did you think of today's email?Your feedback helps me create better emails for you! |