rubenflamshep

When I was going through this it was because OpenAI had defaulted to /fast mode with 2x token usage

Nah, if a human can't be bothered to write it themselves, I can't be bothered to read it.

Hmmm, I disagree. The AI is exceedingly average at everything it does and requires an expert human-in-the-loop to catch things that appear plausible but are slop. To that degree I think there is a difference between "AI generated" and slop.

Some engineers I work with have had less than desirable results with /simplify but it overall seems to work! I used to use some of the humanlayer subagents but they haven't been updated in several months

I find all of these .md files released by the labs to be ai generated slop. The only exception being maybe the /simplify command

This loads some bars and then just breaks for me :(

Very cool! One small UI grip: When I play a song the control at appears in the bottom of the page blocks the footer on the main page.

I assume you looked into automating the charts for new countries/years. What were the blockers for that?

There is no chart or table in the original paper. Feels like the one in the LLM-generated page is probably hallucinated?

I've found VSCode _ok_ to work with across across different workspaces/projects. The window memory is hit and miss. There's a secondary side bar I've been trying to NOT have open on startup but always seem to stick around. I'd prefer to programmatically manage the windows so I can tinker with an automated setup but the VSCode API/Plugins for managing this are terrible and tend to fail silently.

CLI within VSCode is workable but most of my VSCode envs are within a docker container. This is a pattern that I'm moving more and more away from as agents within a container kind of suck.

People are getting caught up in the "fast (but slow) diffusion)" that Dario has spoken to. Adoption of these tools has been fast but not instant but people will poke holes via "well, it hasn't done x yet".

For my own work I've focused on using the agents to help clean up our CICD and make it more robust, specifically because the rest of the company is using agents more broadly. Seems like a way to leverage the technology in a non-slop oriented way

Interesting. What would you say is your ratio of "sit down and make the implementation" time to "multi-agent system builds the thing" time?

Same. The only situation when I've consistently gotten a system to run for 20+ minutes was a data-analysis with tight guardrails and explicit multi-phase operations.

Outside that I'm juggling 2-3 sessions at most with nothing staying unattended for more than 10 minutes.

Quick plus one for Capital One after also working there. They're by far the most tech-forward of all the larger financial institutions, and by virtue of being a FI they take data-security much more seriously than any other "tech" companies.

No this is not a paid post lol

I'm on desktop!

I think the key here is having the network with the high-roller clients. The ability to execute is down funnel of that.

I wrote a local react app that lets you assign specific unit unit sounds from StarCraft II to different CC hooks: https://github.com/rubenflamshepherd/starcraft-claude

It also lets you manage Claude notifications more gracefully than what you get out of the box with CC. Been lazy about putting the finishing touches on it so this is a good kick in the ass to get that done!

It didn’t read as AI to me :)

As someone who has leaned fully into AI tooling this resonates. The current environment is an oligopoly so I'm learning how to leverage someone else's tool. However, in this way, I don't think LLMs are a radical departure from any proprietary other tool (e.g. Photoshop).

Hey, it's really nice you're supporting your wife like this! But there's nothing about how you're using AI as the "Lore Auditor" in the actual post?

1. I would allow users to play around without entering their email. 2. Why can't I just ask ChatGPT to do deep research on a topic for me? 3. What evals do you have to prove that the agents don't hallucinate output that sounds good

Your "How it works button" doesn't work friend

That said, the main issue I find with agentic is my mental model getting desynchronized. No matter how fast the models get, it takes a fixed amount of time for me to catch up and understand what they've done.

This is why I'm so skeptical of anyone running 6+ Claude sessions at a time. I've gotten to 5 but really that was across 3 sessions with 2 standing by just to commit stuff. And even with just 3 sessions I constantly lost where I was and wasted time re-orienting myself, doing work in the wrong session, etc.

The most enjoyable way I've found of staying synced is to stay in the driver's seat, and to command many small rapid edits manually.

Same, there's a fantastic flow state/momentum I can get in a single session just knocking off features. I don't mind switching between two sessions in this state but the experience is better when it's two different projects vs two different features on the same project. The complete context switch lets be re-orient more easily

They used to? I have a distinct memory of it doing exactly that a few months ago. Maybe it got dropped in the mad dash that passes for CC sprint cycles

Without work people devolve into playing video games and smoking pot in their mom's basement.

I have no problem finding fulfilling and meaningful projects outside of my work! There are many people like me :)

Pretty good article until the bizarre post-script where they fall back on the tired "people derive meaning from their work" for why UBI is bad.

will there be a day that AI will know what are "the right things to build" and have the "agency" (or illusion of) to do it better than an AI+human

I share this sentiment. It's really cool that these systems can do 80% of the work. But given what this 80% entails, I don't see a moat around that remaining 20%.

Enjoyed this piece! I use binary search to investigate data pipeline issues. Didn’t think to use it to debug features with agents which was a very cool approach.

Can you believe there are people out there who haven't read this yet? I can, because one of them was me. This was incredible.

A systems programmer will know what to do when society breaks down, because the systems programmer already lives in a world without law.

How much of an ECE background do you have? I've also thought about dabbling in LLM-assisted PCB stuff but felt like I was lacking too much of a foundation to get started (no ECE background at all)

It’s like an echo chamber of the same mannerisms

Hmm, I imagine that a forum made up of slightly different versions of yourself would probably be a variation of this!

Would be interesting to see the first “non-standard” response to see how far out the tails go on the sycophancy-argumentative spectrum.

100% though I do suspect there are human-thumbs on the scale for these non-standard responses that I've been seeing