I tried summarizing the thread so far (339 comments) with a custom system prompt [0] and a user-prompt that captures the structure (hierarchy and upvotes) of the thread [1].

This is the output that we got (based on the HN-Companion project) [2]:

LLama 4 Scout - https://gist.github.com/annjose/9303af60a38acd5454732e915e33...

Llama 4 Maverick - https://gist.github.com/annjose/4d8425ea3410adab2de4fe9a5785...

Claude 3.7 - https://gist.github.com/annjose/5f838f5c8d105fbbd815c5359f20...

The summary from Scout and Maverick both look good (comparable to Claude), and with this structure, Scout seems to follow the prompt slightly better.

In this case, we used the models 'meta-llama/llama-4-maverick' and 'meta-llama/llama-4-scout' from OpenRouter.

--

[0] - https://gist.github.com/annjose/5145ad3b7e2e400162f4fe784a14...

[1] - https://gist.github.com/annjose/d30386aa5ce81c628a88bd86111a...

[2] - https://github.com/levelup-apps/hn-enhancer

edited: To add OpenRouter model details.

This is the script that assembles the structured comments and generates the summary - https://github.com/levelup-apps/hn-enhancer/blob/main/script...

You can run it as: node summarize-comments.js <post_id> Example: node summarize-comments.js 43597782

And the summary will be put in the "output" folder.

You need to set the environment variable (in this case OPENROUTER_API_KEY because LLama4 is currently available at OpenRouter).

as another dateline, Maverick has taken #2 position on LMArena, just behind Gemini 2.5 Pro.

That Gemini 2.5 one is impressive. I found it interesting that the blog post didn't mention Gemini 2.5 at all. Okay, it was released pretty recently, but 10 days seems like enough time to run the benchmarks, so maybe the results make Llama 4 look worse?

I'm sure it does, as Gemini 2.5 Pro has been making every other model look pretty bad.

Meta will most likely compare against it when they release the upcoming Llama 4 reasoning model.

LM Arena ranks it second, just below Gemini 2.5 Pro.

> I'm a little unimpressed by its instruction following

Been trying the 109b version on Groq and it seems less capable than Gemma 3 27b

I have found the Gemini 2.5 Pro summary genuinely interesting: it adequately describes what I've read.

Have you thought about automatizing hn-summaries for say what the 5 top posts are at 8 AM EST?

That would be a simple product to test the market. If successful, it could be easily extended to a weekly newsletter summary.

This is a great idea! Exactly what I was also thinking and started working on a side-project. Currently the project can create summaries like this [1].

Since HN Homepage stories change throughtout the day, I thought it is better to create the Newsletter based on https://news.ycombinator.com/front

So, you are getting the news a day late, but it will capture the top stories for that day. The newsletter will have high-level summary for each post and a link to get the details for that story from a static site.

[1] - https://news.ycombinator.com/item?id=43597782

https://hnup.date/ ;)

yes this is great but I'd like to pick a different voice. the current one feels too robotic

Same, it was using the high quality openai voice until my account ran out of funds.. Now it's using edge-tts which is free. So far it seems like the best option in terms of price/performance, but I'm happy to switch it up if something better comes along.

The gemini example was a wonderful summary of the comments, but audio is not very practical for something that long.

What about putting the text version that's used to make the audio somewhere on the page? (or better, on a subpage where there's no audio playback)

I'll look into it for the next iteration! I could just take the transcript that's already on the page and put it somewhere separate from the audio.

But thinking about it a little more, what would the use case for a text version actually look like? I feel like if you're already on HN, navigating somewhere else to get a TLDR would be too much friction. Or are we talking RSS/blog type delivery?

Here's the link for model on openrouter: https://openrouter.ai/meta-llama/llama-4-maverick

> had a 2048 limit on output size for some reason

It's a common issue with ollama, maybe it's running something similar under the hood?

It doesn’t seem that impressive to me either.