Bài đăng

New top story on Hacker News: Young people aren't as happy as they used to be [Global Flourishing Study]

Young people aren't as happy as they used to be [Global Flourishing Study] 24 by marojejian | 21 comments on Hacker News. April 30, 2025 at 11:19PM marojejian 24 https://ift.tt/bvuxa3y Young people aren't as happy as they used to be [Global Flourishing Study] 21 https://ift.tt/ynDGhFe

New top story on Hacker News: Show HN: Create your own finetuned AI model using Google Sheets

Show HN: Create your own finetuned AI model using Google Sheets 7 by QueensGambit | 0 comments on Hacker News. Hello HN, We built Promptrepo to make finetuning accessible to product teams — not just ML engineers. Last week, OpenAI’s CPO shared how they use fine-tuning for everything from customer support to deep research, and called it the future for serious AI teams. Yet most teams I know still rely on prompting, because fine-tuning is too technical, while the people who have the training data (product managers and domain experts) are often non-technical. With Promptrepo, they can now: - Add training examples in Google Sheets - Click a button to train - Deploy and test instantly - Use OpenAI, Claude, Gemini or Llama models We’ve used this internally for years to power AI workflows in our products (Formfacade, Formesign, Neartail), and we're now opening it up to others. Would love your feedback and happy to answer any questions! --- Try it free - https://ift.tt/SdhfZyF Demo vide...

New top story on Hacker News: Show HN: ART – a new open-source RL framework for training agents

Show HN: ART – a new open-source RL framework for training agents 12 by kcorbitt | 0 comments on Hacker News. Hey HN, I wanted to share a new project we've been working on for the last couple of months called ART ( https://ift.tt/qM6W8t1 ). ART is a new open-source framework for training agents using reinforcement learning (RL). RL allows you to train an agent to perform better at any task whose outcome can be measured and quantified. There are many excellent projects focused on training LLMs with RL, such as GRPOTrainer ( https://ift.tt/qbjGT2J ) and verl ( https://ift.tt/FEU0IvC ). We've used these frameworks extensively for customer-facing projects at OpenPipe, but grew frustrated with some key limitations: - Multi-turn workflows, where the agent calls a tool, gets a response, and calls another, are not well supported. This makes them a non-starter for any task that requires an agent to perform a sequence of actions. - Other frameworks typically have low GPU efficiency. T...

New top story on Hacker News: Why can't Ivies cope with losing a few hundred million?

Why can't Ivies cope with losing a few hundred million? 40 by sneakerblack | 65 comments on Hacker News. April 30, 2025 at 09:36PM sneakerblack 40 https://ift.tt/QM9ibp0 Why can't Ivies cope with losing a few hundred million? 65 https://ift.tt/UWJKjmX

New top story on Hacker News: Everything we announced at our first-ever LlamaCon

Everything we announced at our first-ever LlamaCon 37 by meetpateltech | 11 comments on Hacker News. April 30, 2025 at 12:17AM meetpateltech 37 https://ift.tt/ltjkLNI Everything we announced at our first-ever LlamaCon 11 https://ift.tt/AFouJH6

New top story on Hacker News: Hestus, Inc. (YC S24) Is Hiring an ML Engineer to Revolutionize CAD

Hestus, Inc. (YC S24) Is Hiring an ML Engineer to Revolutionize CAD 1 by sohrabhaghighat | 0 comments on Hacker News. April 30, 2025 at 12:01AM sohrabhaghighat 1 https://ift.tt/S3AXMab Hestus, Inc. (YC S24) Is Hiring an ML Engineer to Revolutionize CAD 0 https://ift.tt/wkGFa2m

New top story on Hacker News: O3 Beats a Master-Level GeoGuessr Player–Even with Fake EXIF Data

O3 Beats a Master-Level GeoGuessr Player–Even with Fake EXIF Data 48 by bko | 32 comments on Hacker News. April 29, 2025 at 11:48PM bko 48 https://ift.tt/J4LDkF3 O3 Beats a Master-Level GeoGuessr Player–Even with Fake EXIF Data 32 https://ift.tt/8fy0zAX