Why? What’s the end goal? Lower cost? Faster analysis?

I configured an agent to respond to pages via Slack. It has access to ClickStack (for telemetry), Kubernetes, and GitHub. It runs one of the Sonnet models. The cost is so low, responding to less than a dozen pages a day (mostly from a very sensitive error count alarm) that swapping got Jev makes zero sense. This is especially true if the results are less trustworthy.

AI coding has taken away those conversations.

It seems LLM usage has eroded whatever facades existed and made some of us believe we were part of teams or organizations that shared these values, or culture, I'm seeing expressed in the article and comments. Perhaps _we_ were the ones hallucinating the values existed in the first place?

I don't begrudge folks who want to solve problems by any means, and not worry about the alienation or deskilling. That's their right. However, it's now clear to me that I have to make a conscious effort to express what my own values are and to build/join and organization that shares them.

The problem arises when it hallucinates answers. That results in colleagues operating based on invalid information, leading to bigger issues. I've seen this many times at my own company, and I simply do not know how to tell folks to be more discerning of the LLM responses while leadership is simultaneously saying do more, faster, with AI.

Comments URL: https://news.ycombinator.com/item?id=49936383

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=49913730

Points: 1

# Comments: 0

Who is your ideal customer? This seems worse for marketers because it's yet another channel to integrate, and the messaging cannot be personalized. The market moved toward personalized marketing years ago, so a channel that lacks personalization seems destined to underperform.

Asking my shoppers/users to download someone else's app seems like a non-starter.

This all seems great for end-users, but terrible for the marketers/organizations that would actually be paying you.

I can see this working for conferences, but most of those have their own apps.

The messages are also limited to text and links, so no MMS.

Customers stopped trusting email because it became overloaded with spam. The incentive from loyalty programs (which is my primary use case) keeps trust high for SMS.

> Does this organization prioritize human learning?

That has been my primary motivator for code reviews. I want to teach and learn from others, especially given the decreasing levels of collaboration due to increased AI usage.

The sad truth is that all of my feedback just goes straight to agents. Maybe 10% is reacted to by a human, so I’m left wondering if there’s any value to a real review aside from poorly training robots to do my job, and further atrophying the abilities of my team members.

The downside, however, is they are also unknowingly digging themselves into holes. For example, we have AI-generated skills that are thousands of lines long and include Python scripts with hundreds of lines of tests. Some of these Python functions are literally just emitting MCP tool names.

I follow the [gateway deployment pattern](https://opentelemetry.io/docs/collector/deploy/gateway/). Everything sends telemetry to our gateway, which exports to ClickHouse (formerly Datadog).

We use Node.js, so all we need to do is run a script initializing Otel before running the app. We set this up following the docs a few years ago, and haven’t had to change it much since then.