Hacker News: rubenflamshep

New comment by rubenflamshep in "Claude Code Unpacked : A visual guide"

rubenflamshep — Wed, 01 Apr 2026 14:47:54 +0000

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

Show HN: Agentic Data Analysis with Claude Code

rubenflamshep — Tue, 10 Mar 2026 16:44:53 +0000

Hey HN, as a former data analyst, I’ve been tooling around trying to get agents to do my old job. The result is this system that gets you maybe 80% of the way there. I think this is a good data point for what the current frontier models are capable of and where they are still lacking (in this case — hypothesis generation and general data intuition).

Some initial learnings: - Generating web app-based reports goes much better if there are explicit templates/pre-defined components for the model to use. - Claude can “heal” broken charts if you give it access to chart images and run a separate QA loop.

Would either feedback from the community or to hear from others that have tried similar things!

Comments URL: https://news.ycombinator.com/item?id=47325702

Points: 6

# Comments: 0

New comment by rubenflamshep in "Show HN: What was the world listening to? Music charts, 20 countries (1940–2025)"

rubenflamshep — Tue, 10 Mar 2026 16:41:59 +0000

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?

New comment by rubenflamshep in "Show HN: Now I Get It – Translate scientific papers into interactive webpages"

rubenflamshep — Sat, 28 Feb 2026 18:04:30 +0000

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

New comment by rubenflamshep in "Pi – A minimal terminal coding harness"

rubenflamshep — Wed, 25 Feb 2026 18:55:39 +0000

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.

New comment by rubenflamshep in "Why is Claude an Electron app?"

rubenflamshep — Sun, 22 Feb 2026 01:20:44 +0000

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

New comment by rubenflamshep in ""Token anxiety", a slot machine by any other name"

rubenflamshep — Tue, 17 Feb 2026 16:14:29 +0000

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

New comment by rubenflamshep in ""Token anxiety", a slot machine by any other name"

rubenflamshep — Tue, 17 Feb 2026 15:52:31 +0000

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.

New comment by rubenflamshep in "I’m joining OpenAI"

rubenflamshep — Mon, 16 Feb 2026 14:51:16 +0000

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

New comment by rubenflamshep in "Startup Idea that stops consumers paying the full price"

rubenflamshep — Thu, 12 Feb 2026 16:33:29 +0000

I'm on desktop!

New comment by rubenflamshep in "I started programming when I was 7. I'm 50 now and the thing I loved has changed"

rubenflamshep — Thu, 12 Feb 2026 16:32:58 +0000

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

New comment by rubenflamshep in "Warcraft III Peon Voice Notifications for Claude Code"

rubenflamshep — Thu, 12 Feb 2026 16:30:47 +0000

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!

New comment by rubenflamshep in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

rubenflamshep — Thu, 12 Feb 2026 15:53:02 +0000

It didn’t read as AI to me :)

New comment by rubenflamshep in "I started programming when I was 7. I'm 50 now and the thing I loved has changed"

rubenflamshep — Tue, 10 Feb 2026 19:02:40 +0000

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).

New comment by rubenflamshep in "Authentically Authoring: Maintaining a 300k-word sci-fi world without AI slop"

rubenflamshep — Sun, 08 Feb 2026 14:15:37 +0000

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?

New comment by rubenflamshep in "Show HN: Team of agent researchers read things I don't have time to and brief me"

rubenflamshep — Sun, 08 Feb 2026 14:05:43 +0000

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

New comment by rubenflamshep in "Startup Idea that stops consumers paying the full price"

rubenflamshep — Sun, 08 Feb 2026 14:03:36 +0000

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

New comment by rubenflamshep in "Beyond agentic coding"

rubenflamshep — Sun, 08 Feb 2026 13:59:58 +0000

> 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

New comment by rubenflamshep in "Speed up responses with fast mode"

rubenflamshep — Sun, 08 Feb 2026 13:15:08 +0000

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

New comment by rubenflamshep in "The AI boom is causing shortages everywhere else"

rubenflamshep — Sat, 07 Feb 2026 23:36:49 +0000

> 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 :)