Viewing profile — jaigupta

When I said forget, I meant that it does not follow instructions in .claude/agents/chrome-tester.md and rather starts working on stuff that was going on in main context. I am not s…

During development or bug hunting, I would want Claude to use Chrome directly. It is very useful. Previously I used to use playwright-mcp and now using Claude Chrome extension. How…

I have used OpenRouter before but in this case I was trying to use it like Claude Code (agentic coding with a simple fixed monthly subscription). I don't want to pay per use via di…

Only if I could figure out how to use it. I have been using Claude Code and enjoy it. I sometimes also try Codex which is also not bad. Trying to use Gemini cli is such a pain. I b…

Yes. Noticed in Claude Code after enabling documents skill then had to disable it for this reason.

We had been colocating servers from decades but there is too much "YOU", compared to that we find Hetzner doing a lot for us (hardware inventory, replacement, remote hands, network…

Same here. Hetzner found no issues with hardware in diagnostics, they insisted it is related to OS/Software side but on my request they changed hardware which fixed issue.

https://docs.hetzner.com/storage/object-storage/faq/general/ What kind of redundancy does Object Storage offer? How resilient is the product to failures? "Each uploaded data object…

We use a cache too but we still will hit this limit because our cache is not very large compared with bucket size and as you said, we need to make HEAD requests. I do not know if t…

To us, 750 operations/s per Bucket and 50,000,000 objects per Bucket are deal breakers. Maybe xx operations/s per TB of storage would have been better since that way large buckets …

What is durability? I can't find this information.

In India, credit cards and even debit cards (which have much lower transaction fee) were never a hit. UPI changed everything, it is easy, convenient and has zero cost for either pa…

They will have to increase transparency (rankings algo, pricing etc), allow data portability for users (and hotels), and avoiding self-preferencing of its services over competitors…

It is about $40/month plan in India for 1GB connection. I am also pretty limited by wireless speeds.

update: I used model AIDC-ai-business_Marcoroni-7B-v3 and it is so much better.

This is my first time running LLM locally. I am running TheBloke/SUS-Chat-34B-AWQ using text-generation-webui. On my simple prompt "Write a story about a village boy" output from L…

We are an SaaS provider and customers demand to be hosted in US for various reasons (a) They think they will get better performance/latency (although in our application it does not…

Really? I don't find them to be of a good value at all. Not just bandwidth but also the baseline network speed limitations based on EC2 size.

Correct. This is the only reason.

How is your experience with OVH?

At present we are using Hetzner AX101/AX102 dedicated servers. They are of great value for money. What provider would you recommend in the US? I understand it may not be as good va…

I meant all Prometheus based solutions, includes Thanos, M3, VictoriaMetrics. Thank you for your answer.

This is about Prometheus but Mimir makes it interesting. I can't find any other open source time series database except Mimir/Cortex which allows this much scale (clustering option…