yeah, see this very often. Less capable models tend to loop more and end up costing more per task, even though they cost less per token.

Daughter loves getting these in the mail, and this paragraph is absolutely right!

>> That year, Parton explained that as well as improving child literacy, “it’s the fact they get recognised. They get this little book with their little name on it in the mail, and they feel special. They start taking pride in themselves, and they know that somebody out there is thinking of [them].”

I'm in a borough of London, and did a bit of a double-take when they told me that Dolly Parton would be sending my daughter a book every month. But indeed she did, and it had exactly that effect, and now she's an absolutely avid reader.

Thank you, Dolly. That meant a lot to us, and millions upon millions of other people too.

Perhaps then, rather than flying flags at half-mast, it'd be better to send that-many books to children around the world. Sadly it seems people calling the shots, the strong of the day, are more interested in delivering threats and ultimatums, rather than what shiny Dolly did.

What an apparent demonstration that not everyone is gifted the same amount of generosity.

You can donate to her charity.

Probably better than whichever flavor of ideological bullshit our politicians would send, anyway.

Very much this.

My kid's nursery gave out books from Dolly. It was a little ceremony, my kid loved it. We still have them.

But I was really surprised, I thought it was joke, why would Dolly care about my Kid's reading? but she really did. She really did care about a bunch of kids in inner city london.

Obviously I am not blessed with millions, but Dolly does lead by example. I need to do better.

When my daughter turned five and received her final book in the mail, it came with a letter that still makes me tear up.

My son loves them too!

Appreciate the detail in this and the previous post on creating internal benchmarks!

Have you all attempted finetuning smaller OSS models on your repos for coding?

We do this for a lot of our customers (fine tuned to save cost when inference volume is high). Right now for internal coding we are using off-the-shelf models but we are considering fine tuning as well to squeeze more efficiency out.

well, at least they are not leaving to be MTS at Anthropic.

Thanks for writing this, and look forward to the one on procedural memory.

Seems like teams are encoding procedural knowledge in skills repositories, and I wonder if there’s additional utility from an auto created procedural memory layer

>> Superlog scans your codebase and infrastructure to add new alerts, metrics and dashboards, preventing tricky failure modes and observability decay.

This is interesting, and my prior belief here has been that this automates a one time set up, and perhaps a quarterly clean-up or reactive monitoring changes that people do today. Curious what your experience has been - do teams accept these ongoing maintenance PRs at a good rate?

For full disclosure / context: we work in a related space - investigation agents for production issues.

This is a very interesting read on failure modes of AI agents in prod.

Curious about this section on the system prompt change: >> After multiple weeks of internal testing and no regressions in the set of evaluations we ran, we felt confident about the change and shipped it alongside Opus 4.7 on April 16. As part of this investigation, we ran more ablations (removing lines from the system prompt to understand the impact of each line) using a broader set of evaluations. One of these evaluations showed a 3% drop for both Opus 4.6 and 4.7. We immediately reverted the prompt as part of the April 20 release.

Curious what helped catch in the later eval vs. initial ones. Was it that the initial testing was online A/B comparison of aggregate metrics, or that the dataset was not broad enough?

>> how the runbooks can self heal if results from some steps in the middle are not expected.

Yeah this is a very interesting angle. Our primary mechanism here is via agent created auto-memories today. The agent keeps track of the most useful steps, and more importantly, dead end steps as it executes runbooks. We think this offers a great bridge to suggest runbook updates and keep them current.

>> Curious how much savings do you observe from using runbook versus purely let Claude do the planning at first.

Really depends on runbook quality, so I don't have a straightforward answer. Of course, it's faster and cheaper if you have well defined steps in your runbooks. As an example, `check logs for service frontend, faceted by host_name`, vs. `check logs`. Agent does more exploration in the latter case.

We wrote about the LLM costs of investigating production alerts more generally here, in case helpful: https://relvy.ai/blog/llm-cost-of-ai-sre-investigating-produ...

Do you mean how we connect to internal data? Today, you can connect any API endpoint to Relvy, so if you have internal business data / dashboards that you look at while debugging, Relvy can do the same if there's an API for it.

Most of our deployments are self-hosted, in which case the data stays locally (your chosen LLM provider exempted), if that's what you are asking.

Nice to see you here, Will! I’d generally recommend using open telemetry for instrumentation so that you keep the option of switching between telemetry vendors.

Re: runbooks, yeah even larger teams don’t have good ones to begin with. Relvy helps debug without runbooks as well - it might take longer to explore, but once you are happy with a particular investigation path the AI took, you can save it as a runbook for more deterministic future executions.