HNHacker News
TopNewBestAskShowJobs

seahorseemoji

89 karma · joined June 23, 2026

submissionscomments
seahorseemoji··on Muse Wonder
Ah, you mean VendingBench [1]

[1] https://andonlabs.com/evals/vending-bench-2

seahorseemoji··on MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis
The way Artificial Analysis keeps changing their weights feels kind of like deciding who the winner should be and making the weights reflect that. They’ve been changing their weights to add more weight to improved long-running agentic capabilities, but doing so means they’re reducing the relative importance of world knowledge and of writing ability.

I’ll grant that maybe world knowledge isn’t that important for these models. But writing ability is important for human understanding, and I think the weird turns of phrase and word choices reflect the labs’ underweighting of the importance of human understanding.

seahorseemoji··on Twitter Viewer – View Twitter Without Account
I wish I understood why the majority of the AI discussions happen on Twitter/X.
seahorseemoji··on Collaborative Human Agent Protocol (CHAP)
People in the comments are rough! I think this looks cool, nice job!
seahorseemoji··on Smevals: A small eval suite for evaluating models, prompts, and harnesses
This seems to be a collab between Simon Willison and the guy behind the Superpowers plugin
seahorseemoji··on The difference between "today's task" and "accretive work"
That’s a good point. I am torn between two competing strains of thought, though:

- on the one hand, time-to-market is super important. Getting to the right place faster is obviously better.

- on the other hand, figuring out right product/right fit is hard, and if a business spends that much cost every 3 days chasing every idea (most of which may be bad ideas), they’ve probably wasted a lot of money.

Obviously token costs are cheaper than developers, and local models would reduce costs still further. But the thought I keep coming to is: maybe there’s a benefit to slowing down and not jumping to implement?

I usually hear the opposite side (better to implement 10 things and throw out 9 of them, easier to react to prototypes, etc.). But I also think the infinity of possible ideas doesn’t get smaller when you throw more engineers or compute at it. You just end up exploring more, possibly bad ideas. This works out if exploring more of the space builds a greater understanding of the problem and increases the likelihood that one of your choices pans out. But the cost of exploring the space isn’t $0 and 0 time.