clintonb

You can choose to not upgrade, or forego Apple TV altogether.

I say this as an Apple shareholder.

So the CyberCab will drive on the ceiling of the Boring Company’s tunnel?

> My guess is that truly skilled contractors in these trades are not hurting for work.

Why? Are you assuming these folks are also good at marketing, or customers are sharing via word of mouth?

I rent. I assume homeowners use AngiesList or Yelp, but those reviews don’t guarantee skill or that someone will be in high demand.

Yes. Invoking an MCP tool is just an HTTP call. You can do it with curl.

> Ultimately, we believe that incorporating Jev-driven diagnosis into an SRE agent’s workflow is a significant step toward effectively combining System One and System Two models.

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.

Ink is cheaper.

I wish! We put on a show for a while with tech spec reviews, but the specs were all AI slop. Now we don't even do that. Folks just work in their silos. I mostly learn of new functionality when I am assigned a code review. My feedback on those reviews is passed to an agent.

AI coding has taken away those conversations.

I've struggled with these feelings over the past week as I take some time away from work and the LLM madness. I miss discussions and debates about architecture and solutions to problems. I miss the curiosity and learning!

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.

I don't see the dependency amongst colleagues as a bad thing. The issues I saw when fielding those questions was folks not doing a simple search across the internal docs to answer the question themselves. Yes, LLMs make this initial search easier, and answer a majority of folks' questions.

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.

> The idea is to give user's control of the messaging and marketers better options. SMS is good for individualized messages like you would get from loyalty programs. Our focus is on broadcasting messages to a group - we don't target an individual user by design.

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.

Neat idea, but all it does is give you control over messaging my users instead of me. They need to use your app maintained by you. That’s a huge risk when SMS “just works”.

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.

I was briefly confused wondering what there is to buy on Spotify if one already has a subscription.

The article could be a little clearer that the treatment is for mental health. I’m still not sure what the treated conditions are. Is this for burnout, depression, or something else?

I am contemplating code review within my own organization, and the question I return to is:

> 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.

I disagree. Most of my prompts are “implement <issue-id>”. The issue has a user story and acceptance criteria that the LLM uses to write a plan and ultimately produce code. None of that matters since the code artifact is what actually gets pushed in the repo, thus the code is what should be reviewed.

There was/is a believe that more folks can unblock themselves with access to AI. There is some truth to this. Our product managers and sales folks are achieving more with Claude and MCPs pointed at tools they use.

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 read this, and I have no clue what it's saying.

(I’m not the person you replied to, but have experience here.)

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.

My company uses Linear. The data presented in this blog post is worthless to me and the company. It can be crudely summarized as “agents and agentic development processes are conducting more Linear operations.” Duh!

The data is aggregated, and you cannot possibly identify a single user from what's been published. I see no issue here.

Altria already does this to some extent. See their Digital Trade Program.

My threshold is three. The third time I duplicate code/behavior is when I start to think about DRYing said code/behavior.

I primarily care about the pull request title and description since we squash-merge and those values end up populating the squashed commit.

> Anyone else finds the LLMs version control discipline lacking?

No? How do you define discipline? Claude code knows how to read and write commits. My team just granted it limited force push access a week ago. We’ve taught it to make more human-friendly commit messages.

What’s missing?

I have the technical acumen and money, but zero desire or time to spend ripping discs. It's far too easy to raid the "five dollar bin" at MoviesAnywhere (like I used to do at Wal-Mart and Best Buy).

Licensing issues like Sony's aside, the studios did MoviesAnywhere right. I can buy the disc (often used) and redeem the code, or buy digitally, and download/stream everywhere that matters to me and my family.

If you already have Elasticsearch, it makes sense to continue utilizing it.

Saying, “just use SQLite” completely dismisses the idea that this is a _shared_ memory across teams. The ability to easily connect to the remote service and have everything “just work” pays dividends when you have dozens or hundreds of users.