#llms

From Cydia to ChatGPT, jailbreaking went from cracking iPhones to liberating LLMs. Here's how it works, who's doing it, and why every AI lab is losing sleep.

How to build a decision-grade scorecard for AI agents The post Stop Evaluating LLMs with “Vibe Checks” appeared first on Towards Data Science.

In February 2025, AI developer Andrej Karpathy posted a tweet (or whatever they call them now on the site formerly known as Twitter) about what he called “vibe coding”: There’s a new kind of coding I call “vibe coding”, where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It’s possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like “decrease the padding on the sidebar by half” because I’m too lazy to find it. I “Accept All” always, I don’t read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I’d have to really read through it for a while. Sometimes the LLMs can’t fix a bug so I just work around it or ask for random changes until it goes away. It’s not too bad for throwaway weekend projects, but

In this piece, we reflect on AIES 2025, and outline the conversations and presentations from a discussion session on LLMs in the context of clinical usage and human rights. This is a crosspost from the latest issue of AI Matters, published by the ACM SIAGI. This year’s conference on artificial intelligence, ethics and society (AIES) […]

The connectors allow the vendor to demonstrate that its LLMs can also deliver business value in other industries.

Tests of how well 19 large language models (LLMs) complete and perform complicated multi-step tasks has shown that they are both error-prone and, in many cases, unreliable. The findings are contained a preprint paper, LLMs Corrupt Your Documents When You Delegate, written by Microsoft researchers  Philippe Laban, Tobias Schnabel and Jennifer Neville based on a benchmark they created called DELEGATE-52 that allowed them to simulate workflows that might be part of a knowledge worker’s tasks. The paper is currently under review. They said that the benchmark contains 310 work environments across 52 professional domains including coding, crystallography, genealogy and music sheet notation. Each environment consists of real documents totaling around 15K tokens in length, and five to 10 complex editing tasks that a user might ask an LLM to perform. And, they stated in the paper’s abstract: “Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors

Tests of how well 19 large language models (LLMs) complete and perform complicated multi-step tasks has shown that they are both error-prone and, in many cases, unreliable. The findings are contained a preprint paper, LLMs Corrupt Your Documents When You Delegate, written by Microsoft researchers  Philippe Laban, Tobias Schnabel and Jennifer Neville based on a benchmark they created called DELEGATE-52 that allowed them to simulate workflows that might be part of a knowledge worker’s tasks. The paper is currently under review. They said that the benchmark contains 310 work environments across 52 professional domains including coding, crystallography, genealogy and music sheet notation. Each environment consists of real documents totaling around 15K tokens in length, and five to 10 complex editing tasks that a user might ask an LLM to perform. And, they stated in the paper’s abstract: “Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors

Introduction Hallucinated citations are one of the most frustrating failure modes of Large Language Models (LLMs). While some "vibe citations" are easy for humans to spot, most seem plausible on first glance and require high levels of technical expertise or time-intensive research to identify. Additionally, the production of

This article discusses how to implement an infrastructure for measuring and controlling overly verbose LLM responses.

Sakana AI and NVIDIA Researchers demonstrate that simple L1 regularization can induce over 99% sparsity in feedforward layers with negligible downstream performance impact, and translate that sparsity into real GPU throughput gains using new sparse data formats and fused CUDA kernels. The post Sakana AI and NVIDIA Introduce TwELL with CUDA Kernels for 20.5% Inference and 21.9% Training Speedup in LLMs appeared first on MarkTechPost.