The point for the cost of a task going down is true but the evidence is not correct : artificial analysis have changed their benches several times over the period shown, hence the cost as well.

Very cool. Did you try any majority vote or some other kind of technique to combine several of them and maybe achieve better results ?

> These lower prices for Luna and Terra are also reflected in how usage is counted against paid subscriptions

Does this seem higher or lower limits ?

Nice idea ! How do you handle duplicates ?

[Assuming you mean duplicate HN submissions]

I normalize the URL and use HN's Algolia search API to find an existing story with a matching URL. I don't currently handle multiple HN submissions of the same article; I just use the matching story I find.

That being said, I could see creating a historical snapshot of all the times an article has been submitted and building a blended comments section in the future.

Blended comments section sounds great! Good work.

Crunched a bit and got a first pass of this working.

https://github.com/twalichiewicz/HNewhere/releases/tag/v1.4....

You can test with https://www.apple.com/iphone/

Never heard of him before but I was amazed how straight to the point yet very easy to grasp it was

Love the email idea

Having the right type of interface makes a huge difference.

It reminds me of when Willow Garage chose to name their bot the TurtleBot, because if they named it anything else, people would think it was fast and capable. But when they called it Turtle Bot, people just kind of liked it and were satisfied with what it did.

At the level of Kimi 3, I probably can code only about 1,000 good tokens per day, too. (thankfully coding isn't my job)

The only data-related lawsuit Anthropic got was the books nah ? And they paid only a minor part as paid agreement compared to what they would have paid losing the trial

In a sense, what eventually gets legalized through settlement or what doesn't provoke a lawsuit isn't that relevant.

The process of creating an LLM involves taking and processing a massive amount of human generated data, roughly all the world's literature/thinking/etc. A large portion remains within these systems. Aside from the legality, ethically that shouldn't belong to any one company.

Yep, that second part of my comment was an article I read about OpenAI and my mind mixed it up with Anthropic. My mistake.

Have you benchmarked it in real condition to test if it truly reduces costs ? I feel like many of those type of tools often end up making the llm more lost about the logs and make it more spend than just feeding the raw logs or letting it code to discover the content itself

100% agree for the harnesses, I always end up using CC when I want to use Opus but a few months ago I had my opencode harness set up but Copilot Pro+ rose too much the prices for me to keep using it… What harness do you prefer using ?

Aren’t we the ones giving money to the VCs in the end of the rain cycle ?