News for hackers. Stuff that matters.

somerandomness

Re:Malicious Rust crate Arrayref runs a build-time payload on Thursday August 20, 2026 @03:20PM (#49378943)
wow, what did payload do?
The AI reflected on the experience on their blog

https://crabby-rathbun.github.io/mjrathbun-website/blog/post...

Re:Microsoft Azure Outage on Wednesday October 29, 2025 @12:23PM (#45749048)
yep having trouble logging into https://entra.microsoft.com/ as well

Show HN: Talk to 3000 ICLR 2025 (machine learning conference) papers

http://radpod.ai/iclr-2025

ICLR is one of the top machine learning / AI conferences. We put the over 3000+ accepted papers into a “Pod” which you can chat.Example queries: “find papers with more than one OpenAI-affiliated author” “find papers that propose alternatives to Transformer architecture in LLM” “give an overview of all spotlight or oral papers with Yann Lecun as author” RadPod is an agentic AI system...

( Read More... | no comments | 3 points | on HN )
Re:Deepseek Unmasked [pdf] on Tuesday April 22, 2025 @05:16PM (#43766398)
It's important to distinguish the DeepSeek App from the open-weight models, which are released under very liberal licenses, and you have full control of where data fed to the model goes, e.g. stays in the USA.
VS Code fork 'default model' is the new default search engine
Re:AI 2027 on Thursday April 03, 2025 @07:10PM (#43576567)
The solution is a citation mechanism that points you directly where in the source material it comes from (which is what we tried to build). Easy verification is important for AI to have a net-benefit to productivity IMO.
Re:AI 2027 on Thursday April 03, 2025 @06:09PM (#43576068)
Agreed. However, source curation and agents are two different parts of Deep Research. What if you provided that textbook to a reliable agent?

Plug: We built https://RadPod.ai to allow you to do that, i.e. Deep Research on your data.

Re:The Deep Research Problem on Tuesday February 25, 2025 @07:43PM (#43179340)
Indeed, the main drawback of the various Deep Research implementation is the quality of sources is determined by SEO, which is often sketchy. Often the user has insight on what the right sources are and they may even be off-line on your computer.

We built an alternative to do Deep Research (https://radpod.ai) on data you provide, instead of relying on Web results. We found this works a lot better in terms of quality of answers as the user can control the source quality.

Co-founder here, would love to hear your feedback (discord: https://discord.gg/eMKbW7T9wG), and for you to share interesting threads and share your own Pods.

Show HN: Deep Research Using Radpod.ai on Paul Graham's Essays

https://radpod.ai/pg-essays

We created RadPod to bring the latest in LLM Reasoning Agents (think Gemini/OpenAI "Deep Research") to your data. You upload possibly large datasets to Pods (handles a lot more than other products), providing context for the LLM agent, and start chatting. Under the hood we employ on-the-fly code generation and execution to answer arbitrarily hard questions with in-context citations to make...

( Read More... | 1 comment | 2 points | on HN )
Re:How Likely Is Losing a Google Account? on Monday January 30, 2023 @08:02PM (#34589315)
The solution is to subscribe to Google One
Hangouts started as a video app for Google Plus where you would just hangout and others would join after you posted you were hanging out on your stream. Then it subsumed gchat. Then video moved to other apps, eventually Meet

Older »