jamestimmins

Its reasonable to dislike a bad product experience, but its strange to draw a conclusion of AI altogether based on a tool with limited usage (I've never heard of it).

That's like saying smart watches are useless based on trying out the smart watch made by will.i.am's tech company rather than Apple's.

This is a good point about quality of life. I focused on money in my original comment, but I've heard a lot of people complain that unions have kept them working with their worst coworkers. That alone is a dealbreaker for me.

I've been laid off. It was fine because software is literally the most marketable skill in the world.

Edit: But also, this was a pre-profit VC-backed company. If those companies can't lay people off, it's not like you make good money with more job security. Either the company just has less runway (so I still lose my job, just later and with everyone else) or they adapt by hiring fewer people at lower salaries.

As a California tech worker (where the article is focused), I have zero interest in joining a union and firmly believe that much of what has been possible as a tech employee (high paying, interesting career) is in part because we don't have unions, and instead employees own equity and get valuable skills.

Modern tech workers arguably have the best career deal in the history of humankind. I see no upside in killing the goose with the golden egg.

AI seems to struggle most when it has to make decisions with lots of trade-offs, especially where the context or implications of various decisions are nested, which is presumably why it struggles to write full software systems that are well-designed.

By comparison, financial advice is pretty simple, and there is a universally agreed-upon approach that most people should follow to maximize long-term financial health.

The issue I have with loops is that for truly complex work, where I care about building a generalized solution for a complex problem, the agents frequently reward hack and end up burning indefinitely without finishing until I step in.

Curious how you're addressing this

Telemetry tooling for local Claude/Codex usage so I can analyze old sessions and fill tooling gaps, make sure I'm using the right models for various tasks, update my processes, etc.

I've also replaced Linear with a local sqlite-backed tool, added tooling to speed up code nav, and am building "no-slop", a tool for enforcing architectural guidelines on vibe-coded projects.

This looks awesome. I’m the ideal customer for this and am delighted it exists.

My first thought was my finance professor telling us that companies always raise with equity when they think their equity is overvalued.

The responses to this are wild. I have worked with and built smaller systems like this and it is an incredible speed up.

So much reflexive hate against a genuinely transformative tech. Yes AI has annoying people and grifters, but it is genuinely incredible at some things and finding out how to use it effectively within a company is the most fun I’ve had in my career.

The issue of it burning through tokens grepping around should be fixed with language server integration, but that’s broken in Claude Code and the MCP code nav tools seem to use more tokens than just a home-built code map in markdown files.