Hacker News with Generative AI: Generative AI

Exploring model welfare (anthropic.com)
Human welfare is at the heart of our work at Anthropic: our mission is to make sure that increasingly capable and sophisticated AI systems remain beneficial to humanity.
AI, Ethics, Safety, Generative AI
9 points by psychanarch 18 hours ago | 7 comments
The Policy Puppetry Attack: Novel bypass for major LLMs (hiddenlayer.com)
Researchers at HiddenLayer have developed the first, post-instruction hierarchy, universal, and transferable prompt injection technique that successfully bypasses instruction hierarchy and safety guardrails across all major frontier AI models.
Generative AI, Security, AI Safety
272 points by jacobr1 20 hours ago | 208 comments
The State of Reinforcement Learning for LLM Reasoning (sebastianraschka.com)
A lot has happened this month, especially with the releases of new flagship models like GPT-4.5 and Llama 4. But you might have noticed that reactions to these releases were relatively muted. Why? One reason could be that GPT-4.5 and Llama 4 remain conventional models, which means they were trained without explicit reinforcement learning for reasoning.
Generative AI, Reinforcement Learning
7 points by yaiml 1 day ago | 0 comments
Docker Model Runner Brings Local LLMs to Your Desktop (thenewstack.io)
Docker, Generative AI, Machine Learning, Software
5 points by CrankyBear 2 days ago | 0 comments
Show HN: Lemon Slice Live – Have a video call with a transformer model (ycombinator.com)
Hey HN, this is Lina, Andrew, and Sidney from Lemon Slice. We’ve trained a custom diffusion transformer (DiT) model that achieves video streaming at 25fps and wrapped it into a demo that allows anyone to turn a photo into a real-time, talking avatar.
Generative AI, Machine Learning, Video, Artificial Intelligence, Demo
192 points by lcolucci 2 days ago | 81 comments
One Prompt Can Bypass Every Major LLM's Safeguards (forbes.com)
Security, Artificial Intelligence, Generative AI
40 points by TechTalker22 2 days ago | 1 comments
Show HN: High-performance GenAI engine now open source (github.com/arthur-ai)
Make AI work for Everyone - Monitoring and governing for your AI/ML
Generative AI, Open Source, Artificial Intelligence, Machine Learning
20 points by fryz 2 days ago | 12 comments
Ask HN: Share your AI prompt that stumps every model (ycombinator.com)
I had an idea for creating a crowdsourced database of AI prompts that no AI model could yet crack.
Generative AI, Community, Crowdsourcing
406 points by owendarko 2 days ago | 610 comments
Llama 4 Smells Bad (fastml.com)
Meta has distinguished itself positively by releasing three generations of Llama, a semi-open LLM with weights available if you ask nicely (and provide your full legal name, date of birth, and full organization name with all corporate identifiers). So no, it’s not open source. Anyway, on Saturday (!) May the 5th, Cinco de Mayo, Meta released Llama 4.
AI, Open Source, Meta, Generative AI
41 points by alexmolas 2 days ago | 26 comments
Major Concern – Google Gemini 2.5 Research Preview (ycombinator.com)
Does anyone else feel like Google Gemini 2.5 Research Preview has been created with the exact intent of studying the effects of using indirect and clarifying/qualifying language?
Generative AI, Google
9 points by slyle 2 days ago | 1 comments
Teaching LLMs how to solid model (willpatrick.xyz)
It turns out that LLMs can make CAD models for simple 3D mechanical parts. And, I think they’ll be extremely good at it soon.
Generative AI, 3D Modeling
316 points by wgpatrick 3 days ago | 105 comments
Advancing Invoice Document Processing at Uber Using GenAI (uber.com)
Generative AI, Document Processing, Business Applications, Uber
4 points by benocodes 3 days ago | 0 comments
The Outlook for Programmers (cacm.acm.org)
The job market for programmers is cooling, part of the continuing impact of generative AI and large language models.
Programming, Job Market, Generative AI
45 points by pseudolus 3 days ago | 85 comments
Values in the wild: Discovering values in real-world language model interactions (anthropic.com)
People don’t just ask AIs for the answers to equations, or for purely factual information. Many of the questions they ask force the AI to make value judgments.
Generative AI, Language Models, Artificial Intelligence, Ethics, Research
5 points by miles 4 days ago | 1 comments
New ChatGPT Models Seem to Leave Watermarks on Text (rumidocs.com)
The newer GPT-o3 and GPT-o4 mini models appear to be embedding special character watermarks in generated text.
Generative AI, AI Safety
28 points by croes 4 days ago | 9 comments
Lessons Learned Writing a Book Collaboratively with LLMs (ycombinator.com)
I recently finished a months-long project collaborating intensively with various LLMs (ChatGPT, Claude, Gemini) to write a book about using AI in management.
Generative AI, Book Writing, Management
16 points by scottfalconer 4 days ago | 7 comments
More than 100 public software companies are getting 'squeezed' by AI (businessinsider.com)
A foundational shift is underway in enterprise software, and it's being driven by generative AI.
Generative AI, Software, Business, Artificial Intelligence, Enterprise Software
5 points by bradac56 5 days ago | 2 comments
Making AI-generated code more accurate in any language (news.mit.edu)
Programmers can now use large language models (LLMs) to generate computer code more quickly. However, this only makes programmers’ lives easier if that code follows the rules of the programming language and doesn’t cause a computer to crash.
Generative AI, Programming, Artificial Intelligence
6 points by CharlesW 5 days ago | 0 comments
LLM-powered tools amplify developer capabilities rather than replacing them (matthewsinclair.com)
Last month, I used Claude Code to build two apps: an MVP for a non-trivial backend agent processing platform and the early workings of a reasonably complex frontend for a B2C SaaS product. Together, these projects generated approximately 30k lines of code (and about the same amount again thrown away over the course of the exercise). The experience taught me something important about AI and software development that contradicts much of the current narrative.
Generative AI, Software Development, Programming, Artificial Intelligence
343 points by matthewsinclair 5 days ago | 238 comments
New ChatGPT Models Seem to Leave Watermarks on Text (rumidocs.com)
The newer GPT-o3 and GPT-o4 mini models appear to be embedding special character watermarks in generated text.
Generative AI, Language Models, Security
19 points by hosein88 5 days ago | 27 comments
The State of Reinforcement Learning for LLM Reasoning (sebastianraschka.com)
A lot has happened this month, especially with the releases of new flagship models like GPT-4.5 and Llama 4. But you might have noticed that reactions to these releases were relatively muted. Why? One reason could be that GPT-4.5 and Llama 4 remain conventional models, which means they were trained without explicit reinforcement learning for reasoning.
Reinforcement Learning, Generative AI, AI Research
9 points by jonbaer 5 days ago | 0 comments
To Make Language Models Work Better, Researchers Sidestep Language (quantamagazine.org)
Language isn’t always necessary. While it certainly helps in getting across certain ideas, some neuroscientists have argued that many forms of human thought and reasoning don’t require the medium of words and grammar. Sometimes, the argument goes, having to turn ideas into language actually slows down the thought process.
Generative AI, Science, Language Models, Neuroscience
25 points by jxmorris12 6 days ago | 6 comments
Jagged AGI: o3, Gemini 2.5, and everything after (oneusefulthing.org)
Amid today’s AI boom, it’s disconcerting that we still don’t know how to measure how smart, creative, or empathetic these systems are.
Artificial Intelligence, Generative AI, AI Safety
263 points by ctoth 6 days ago | 338 comments
Maybe Meta's Llama claims to be open source because of the EU AI act (simonwillison.net)
I encountered a theory a while ago that one of the reasons Meta insist on using the term “open source” for their Llama models despite the Llama license not actually conforming to the terms of the Open Source Definition is that the EU’s AI act includes special rules for open source models without requiring OSI compliance.
Generative AI, Open Source, AI Regulations, EU
28 points by code_reader 6 days ago | 14 comments
Show HN: LettuceDetect – Lightweight hallucination detector for RAG pipelines (github.com/KRLabsOrg)
LettuceDetect is a lightweight and efficient tool for detecting hallucinations in Retrieval-Augmented Generation (RAG) systems. It identifies unsupported parts of an answer by comparing it to the provided context.
Generative AI, Tools
10 points by justacoolname 7 days ago | 1 comments
Inferring the Phylogeny of Large Language Models (arxiv.org)
This paper introduces PhyloLM, a method adapting phylogenetic algorithms to Large Language Models (LLMs) to explore whether and how they relate to each other and to predict their performance characteristics.
Machine Learning, Generative AI, AI Research
68 points by weinzierl 7 days ago | 6 comments
New OpenAI models hallucinate more (slashdot.org)
Generative AI, Artificial Intelligence, AI
5 points by pixiemaster 7 days ago | 2 comments
CaMeL: Defeating Prompt Injections by Design (arxiv.org)
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment.
Generative AI, Security
71 points by tomrod 7 days ago | 16 comments
Hands-On Large Language Models (github.com/HandsOnLLM)
Generative AI, Programming
147 points by teleforce 7 days ago | 17 comments
Why R the Critical Value and Emergent Behavior of Large Language Models Fake? (cacm.acm.org)
Why there are no emergent properties in Large Language Models.
Generative AI, Artificial Intelligence, Research, Language Modeling
11 points by eferdinand 7 days ago | 13 comments