News for hackers. Stuff that matters.

andylizf

Show HN: Nonstop, two files that keep Claude Code working while you sleep

https://github.com/andylizf/nonstop

I use Claude Code for big tasks overnight maybe twice a week. About 70% of the time I come back to nothing. It stopped in the first few minutes because it had a question. Or hit a permission error on step 2 of 47 and just sat there. All night.nonstop is my fix. Two files, no dependencies.Before you walk away, /nonstop makes Claude do a pre-flight. It thinks through the whole task, asks every...

( Read More... | no comments | on HN )
Update: My account has been re-enabled this morning. Google apologized for the delay.

To clarify some questions in the comments:

This was a personal account. I normally use my university account for research. I hadn't even used up the $200 free trial, just doing some inference.

I had multiple projects for different AI Studio purposes. Google's automated system likely flagged this as an attempt to circumvent quota limits, even though I was just organizing different use cases into separate projects.

The "2 years" wasn't me ignoring it. I followed up multiple times over this period, but every attempt went nowhere - just automated replies. Eventually I got fed up and decided to post here.

I wasn't paying for support since it was just a personal account for small experiments.

Thanks everyone. The HN visibility definitely helped.

Google Cloud suspended my account for 2 years, only automated replies

My Google account has been suspended from GCP since March 2024.I have submitted multiple appeals through [email protected] over 2 years. Every time I get the same automated template asking me to explain, I reply with details, then nothing. No human ever responds.Case: #1-8622000037271Timeline: - March 2024: Suspended, appeal submitted - April 2024: Automated requests for info, I...

( Read More... | 102 comments | 60 points | on HN )
Re:AI Discovers Algorithm That Beats NSDI'24 Best Paper on Thursday October 30, 2025 @01:47PM (#45762863)
Author here. We used ADRS to automatically evolve a scheduling algorithm starting from a simple greedy policy. Surprisingly, it outperformed Uniform Progress, the NSDI'24 best paper algorithm by discovering "selective waiting" strategies and adaptive pattern recognition.

Counter-intuitive finding: starting from a weaker baseline (greedy) worked better than starting from the SOTA algorithm. The AI found new insights rather than incremental improvements.

The entire process took 5 hours and cost <$20. We're open-sourcing everything and have applied this to other systems problems (MoE load balancing with 5x speedup, see https://news.ycombinator.com/item?id=45688236).

Happy to answer questions about the methodology or results!

Re:How I code with AI on a budget/free on Sunday August 10, 2025 @04:02AM (#44853587)
Yeah, this seems a really fantastic summary of our ideal local AI stack. A powerful, private memory layer has always felt like the missing piece for tools like Cursor or aider.

The idea of this tiny, private index like what the LEANN project describes, combined with local inference via Ollama, is really powerful. I really like this idea about using it in programming, and a truly private "Cursor-like" experience would be a game-changer.

Yeah that's it. My bad lol
Exactly. That's because instead of just mapping keywords, vector search stores the rich meaning of the text as massive data structures, and LEANN is our solution to that paradoxical inefficiency.
Yeah, that's a fair point at first glance. 50GB might not sound like a huge burden for a modern SSD.

However, the 50GB figure was just a starting point for emails. A true "local Jarvis," would need to index everything: all your code repositories, documents, notes, and chat histories. That raw data can easily be hundreds of gigabytes.

For a 200GB text corpus, a traditional vector index can swell to >500GB. At that point, it's no longer a "meager" requirement. It becomes a heavy "tax" on your primary drive, which is often non-upgradable on modern laptops.

The goal for practical local AI shouldn't just be that it's possible, but that it's also lightweight and sustainable. That's the problem we focused on: making a comprehensive local knowledge base feasible without forcing users to dedicate half their SSD to a single index.

This is fantastic work. The focus on a local, sandboxed execution layer is a huge piece of the puzzle for a private AI workspace. The `coderunner` tool looks incredibly useful.

A complementary challenge is the knowledge layer: making the AI aware of your personal data (emails, notes, files) via RAG. As soon as you try this on a large scale, storage becomes a massive bottleneck. A vector database for years of emails can easily exceed 50GB.

(Full disclosure: I'm part of the team at Berkeley that tackled this). We built LEANN, a vector index that cuts storage by ~97% by not storing the embeddings at all. It makes indexing your entire digital life locally actually feasible.

Combining a local execution engine like this with a hyper-efficient knowledge index like LEANN feels like the real path to a true "local Jarvis."

Code: https://github.com/yichuan-w/LEANN Paper: https://arxiv.org/abs/2405.08051