mfrye0

> The IRS, for a time, would cut off your call if their wait system was too busy. That's a critical system in kafkaesque hellscape.

I had to call the IRS this spring and it was hell. I repeatedly was on hold for 1+ hour(s) then get hung up on. Or someone would finally answer, I'd explain, they'd put me on hold for another hour, then just hang up on me. A total of 10+ hours collectively waiting to finally have my questions answered in 10 minutes.

That said, I'd love if the IRS had an AI, where I could send my AI to go deal with it on my behalf. Then if it truly requires a human in the loop, we schedule accordingly vs me on the phone for 10 hours.

Long time user of your embedding models. I'm trying to understand how this works and if I can leverage it.

It sounds like this is a new layer on top of your existing storage layer? So to use this, would I need to give you all of my data first? Or is there a version that can be run on prem?

Another point not really mentioned in here is the type of home. Buying a condo has absolutely been the worst decision of my life.

It was our first home after getting married. The condo HOA will probably go down as the most disfunctional HOA in California history - not exaggerating. It has/will cost an obscene amount of time/money that I will never get back.

Interesting idea, but just about everything is failing for me. Probably the HN hug of death happening.

  Gemini generateContent request failed: { "error": { "code": 429, "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/rate-limit. ", "status": "RESOURCE_EXHAUSTED", "details": [ { "@type": "type.googleapis.com/google.rpc.Help", "links": [ { "description": "Learn more about Gemini API quotas", "url": "https://ai.google.dev/gemini-api/docs/rate-limits" } ] } ] } }

Yes. Have a lawyer and there is indeed meaningful money at stake. I'm more wishing there was a simpler way to go about it though, as it's likely going to cost 6 figures when it's all said and done.

I would love something like this to use with my HOA. About to start mediation and the estimate for the mediator alone is ~$20k.

Relevant data point on AWS - GCP is giving out a ton of cloud credits to startups. On average $100k in comparison to $10k-20k from AWS.

Before Claude Code, a full cloud migration could easily be a couple months. We migrated our whole stack to GCP in about a week. It's trivial to switch clouds now with K8 stack and Claude Code.

I was looking for a version of a proxy that could maximize throughput to each LLM based on its limits. Basically max requests and input/output tokens per second.

I couldn't find something, so I rolled a version together based on redis and job queues. It works decently well, but I'd prefer to use something better if it exists.

Does anyone know of something like this that isn't completely over engineered / abstracted?

Thanks for this. That makes sense.

I've been keeping an eye on this space for awhile as it matures a bit further. There's been a number of startups that have popped up around this - apart from Temporal and DBOS, Hatchet.run looked interesting.

I've been using BullMQ for awhile with distributed workers across K8 and have hacked together what I need, but a lightweight DAG of some sort on Postgres would be great.

I took a brief look at your docs. What would you say is the main difference of yours vs some of the other options? Just the simplicity of it being a single sql file and a sdk wrapper? Sorry if the docs answer this already - trying to take a quick look between work.

I was going to say the same. We're using binary vectors in prod as well. Makes a huge difference in the indexes. This wasn't mentioned once in the article.

I noticed the template too. Someone mentioned recently that's actually a good risk signal - scammers often use the same site structure across domains.

On the research, you're absolutely right. It fits that sweet spot where it's just easy / boring / tedious enough to automate with the current generation of LLMs.

Hey, good question. Yeah, we're aware of many companies that can have thousands of subsidiaries.

We found that going both up the chain and down / sideways in the chain was too much for the agent to handle - they are two distinct operations. The #1 use case was customers trying to understand the ultimate parent, so we decided to focus on that first.

We have something roughly working on subsidiaries, but it's not ready for prime time yet. It would likely be a separate API.

Thank you! Yeah, I know it's a fine balance between shipping too early and having a buggy product vs too late. I'm shipping as fast as I can now to keep that tight feedback loop going.