Viewing profile — nyellin

No, because every article will devolve into a discussion on if AI generated or not, and to what degree. Let content speak for itself.

OP here and the doctor was wonderful. If we fixed the interface they could help more patients in the same time.

It's a trade-off. In these scenarios we update our staging data for next time.

How does copy pasting an error into an LLM involve thinking?

I'm the OP and wanted to clarify. We do not give Claude Code access to production API keys. The intent was staging databases and I've updated the post to make it more clear. We ass…

I'm the OP and this is the exact point of the post. Whoever handed you that project did not have Claude code running it end to end in a production-like environment. Whether you lik…

As written elsewhere, we dont give access to prod! The DBs are staging and our assumption is that every key we give Claude will be leaked. I'll update the post to clarify

Fair enough, I will update

I'm the OP and to clarify we dont give access to prod DBs. The point is you need to give the LLM the ability to test end to end, and that can be done with staging data.

OP here: we don't give Claude Code access to prod. Everything is isolated cloud accounts for this purpose. E.g. we give Claude credentials for db - but it's never prod data.

No, it was designed on paper by someone with no understanding of prompt caching and no consideration of latency or token costs

Why does Atlassian need to train AI models?

Is it possible to run a Kubernetes cluster inside one? (E.g. via KIND.) If so, we'd very much like to test this. We make extensive use of Claude Code web but it can't effectively t…

Is there a safe way to give agents a credit card with usage caps? Ideally also the ability for purchases to pend until human approval.

We publish the benchmarks for HolmesGPT (CNCF sandbox project) at https://holmesgpt.dev/development/evaluations/

HolmesGPT maintainer here: our benchmarks [1] tell a very different story, as does anecdotal evidence from our customers- including Fortune 500 using SRE agents in incredibly compl…

Haiku is called often, but not always the way you think. E.g. every time you write something CC invokes Haiku multiple times to generate the 'delightful 1-2 word phrase used to ind…

Not necessarily true. Subagents allow for parallelization but they can decrease accuracy dramatically if you're not careful because there are often dependencies between tasks and s…

Forgot to address the easiest part: > - how can I reliably call tools with the right schema? This is typically done by enabling strict mode for tool calling which is a hermetic sol…

Re (1) use a TODOs system like Claude code. Re (2) also fairly easy! It's just a summarization prompt. E.g. this is the one we use in our agent: https://github.com/HolmesGPT/holmes…

There's a bit more to it! For example, the agent in the post will demonstrate 'early stopping' where it finishes before the task is really done. You'd think you can solve this with…

Hi HN, I'm Natan from Robusta.dev. We open-sourced HolmesGPT, an AI agent to help on-call engineers triage and respond to alerts. It pulls observability data from your existing too…