Newsfeed

@thepatwalls Interested; with a possibly naïve question: How (if at all) can this help get my content to new members of my target audience?

@rails @dhh PS: Here's the earliest commit as far as I could find <3

Amazing, I didn't know this existed! I started using Rails about 1 year later.

After writing web apps with Java servlets (and liking it), rails new and rails generate felt like pure magic.

If anyone is interested, I built a git-history explorer for rails here (with a focus on the people involved). It starts with the first svn commit on Nov. 24th 2004.

@ryancarson Oh. Good question. The most bottom-left key. Keychrons have a dedicated "macOS" hardware toggle, so I haven't needed much custom mapping. I think.

Keychron K8, hot-swappable, with silent tactile switches! Great feel, good price aaand without cluck-annoying your team on-site :)

@ryancarson I'm not 100% sure if that's what you mean with gitui but me and a colleague have added delegating tasks to Claude Code via Github issues and actions. The PR then becomes the UI.

@ryancarson Anecdotal: I switched to Claude Code full-time six months ago. Whenever I do come back to Cursor/VS Code, it feels over-engineered and clunky.

I think that's the one I saw. Where the main story concluded (the satellite crashed!). Suddenly it went a whole other direction for another eternity?

I do remember, in the first scene, a sort of cyberpunk setting with stationary personal screens. I thought that was pretty nifty :)

@elder_plinius Just discussed this with my friend Alex over dinner: after all is said and done, does it still matter is it's AI or not?

Holy moly, you're right! On Tomcat 5 we had server.xml, web.xml, context.xml and tomcat-users.xml, JNDI data source for mysql and them beans on top.

I think it took me two painful years to really grok this whole setup to get basic CRUD working.

Still, I'm super grateful for those years because Rails was the painkiller I didn't even know I needed.

• rails new my-app suddenly did 90% of the directory setup and config heavy-lifting
• rails generate model|controller|migration|scaffold took all boilerplate out of my hand
• ActiveRecord's validation and relationship semantics allowed me to literally write out what I wanted (in plain English!)

I hope that those who start making stuff today with AI have the same magic "wow!" moment that I felt in 2006 with Rails.

@bb_fresh @theo I genuinely loved this stack. Tomcat was solid. Java 7 with Eclipse rocked and JSP was easy to write. I switched to Rails in 2006 but have only fond memories here.

@ZoldenGames Laser-worm is my favorite :) Thank you for sharing!

@vatsal_manot @arvidkahl PS: For reference, here's the full 4o chat + result (including my prompt and transcript) so you can eyeball it against the local response:

(Can't share the one I mentioned because it's a confidential conversation from my wife's work)

But I just did another test with a similar interview I conducted with a friend of mine a few years back.

Here I did the analysis "leg-work" myself, so I can speak to the results from the LLMs.

Setup
Chip: Apple M4 Max
Memory: 128 GB
macOS: 15.4.1

Models

• OpenAI Model: ChatGPT 4o (via web, no customizations)
• Local Llama4 Model (via ollama run llama4)

- parameters 108.6B
- context length 10485760
- embedding length 5120
- quantization Q4_K_M

Prompt
"Check this interview I did with Jonathan. Summarize the overall conversation and extract the most important insights. Here's the transcript: <paste of the transcript>"

Transcript
Text input: ~38,400 characters
Input language: English, casual and inquisitive
Tokens: ~9,820

One-Shot Results

ChatGPT 4o:

• The summary is thoughtful and thourough.
• The insights are on-point and at least as good, if not better, than mine.

Here's the first half of the response

```chat

[Prompt + transcript]

# Summary of the Conversation
Jonathan is a photographer who recently shifted his full focus to photography after ending his coaching commitments. He’s been in “training mode” for the past three months and now feels that he’s reached a new level professionally. His days are packed with client shoots—mainly assisting his partner Lindsey with elopements and couple sessions—leaving little time to edit or build his own portfolio.

He currently struggles most with a backlog of unedited shoots (12+ “messy kitchens”), which prevents him from building his own brand and attracting independent clients. The editing process is particularly time-consuming because he is still developing his personal editing style from scratch and refuses to rely on presets that would limit his learning.

Despite this, he’s highly motivated, journaling his learning daily and constantly experimenting. He values the process and wants to do things the right way, not the fast way. He also described moments of imposter syndrome and anxiety when comparing older work to his improving eye.

The conversation evolved into how his editing bottleneck might be supported, leading to a surprising and heartfelt idea: home-cooked meals by grandmas, delivered or picked up, to reduce the burden of cooking and create space for editing while offering emotional nourishment and routine.

chatgpt.com/share/6828b2e6…

```

Llama4:

• The summary is literal, unimaginative and bland.
• The summary only picks up on one small point ("home-cooked meals") but drops the other 80% of topics.
• There is no mention of insights even though clearly required in the prompt

```chat

[Prompt + transcript]

This conversation appears to be a transcribed interview between two individuals. I'll provide a summarized version of the conversation:

The conversation revolves around the idea of having meals prepared by a grandmother-like figure and delivered to one's home. The speaker seems to
appreciate the idea of having home-cooked meals without the hassle of cooking.

The speaker also brings up the idea of wanting to have meals that are home-cooked and delivered to his place. He seems to like that idea a lot. The
idea is that there will be like meals that are prepared and then delivered.

The speaker also seems to be appreciative of having a meal prepared by someone else, delivered at his own home.

There are lot's of conversation going on. There are a lot's of different meals and lot's of different conversation going on

There are different ideas discussed about meals being delivered and speaker like that idea a lot.

The person also seems like to be appreciative. The person seems to like that idea lot.

He seems like, he seems to be appreciative. The idea seems to like.

This conversation seems to be transcript of two people having conversation .There are lot's of ideas discussed about meals and different kind
conversation. There are lot's of different meal's and lot's of different conversation.

>>> What are the most surprising insights?

The conversation appears to be fragmented and open-ended. Some possible insights that can be gathered from this conversation are:

* The speaker seems to appreciate the idea of having home-cooked meals without the hassle of cooking.
* The speaker likes the idea of having meals delivered to their home.
* The conversation is casual and conversational, with no clear structure or topic.

Some possible surprising insights that can be gathered from this conversation are:

* The speaker's appreciation for home-cooked meals and the desire for convenience.
* The speaker's casual and conversational tone.

However, it's worth noting that the conversation is quite fragmented and doesn't provide a clear narrative or specific insights. If you have more
context or information, I'd be happy to try and provide more specific insights.
```

So maybe I'm missing some obvious config?

@signulll LOL!

Hey Arvid! My wife and ran a local LLM experiment inspired by your post last weekend ("Local LLMs" are a must-consider option for every SaaS that wants to deal with private customer data...").

After comparing results, I'm actually conflicted about the whole thing.

For context:

My wife does leadership coaching and recently used vanilla GPT-4o via ChatGPT to summarize a text-transcript of an hour-long conversation.

Over the weekend, I read your post and thought "Hey, let's test local LLMs for more privacy control. The open source models must be pretty good in 2025."

So I installed Ollama + Open WebUI plus five models on a 128GB MacBook Pro.

I am genuinely dumbfounded about the actual results we got today of comparing ChatGPT/GPT-4o vs. Llama4, Llama3.3, Llama3.2, DeepSeekR1 and Gemma.

In short: Compared to our reference GPT-4o output, none (as in NONE, zero, zilch, nil) of the open source models were able to create even a basic summary based on the exact same prompt + text.

In my opinion, the open source summaries were offensively bad. It felt like reading the most bland, generic and idiotic SEO slop I've read since I last used Google. None of the obvious topics mentioned in the text were part of the summary. Just blah. I tested this with 5 models to boot! I ran the same test twice for each.

I'm not an OpenAI fan per se, but if this is truly OS/SOTA then, we shouldn't even mention Llama4 or the others in the same breath as the newer OpenAI models.

What do you think?

Research job #1 is like a personal eval of sorts:

The topic is very niche and I've got a good grasp of the "fact-portion" of the answer. So it's not facts I'm looking for but nuances I might have missed.

I guess my squishy metric here is "Surprisal" (aka Shannon information).

Prompt: 'Can you give me a summary who/what/why/how/where/when of "Chances With Wolves"?'

Now I wonder: Is this even a good task for Scout in the first place?

Research job #1 started!

Note on signing up:

• I clicked on the "Sign up with Google" and nothing happened.
• I then saw the "I'm a human" captcha at the bottom, figured maybe that's needed.
• I was unsure if clicking it would break the current flow so I waited.
• After 20 seconds I was like "Eh, it's already broken. What's the worst that can happen" and clicked the captcha
• which then immediately forwarded me to Google and a successful signup.

@emollick would love to hear your thoughts on this!