Viewing profile — sgk284

I ran them for a very short time!

Hey HN, one of the side projects my startup maintains is this arena of 52 apps implemented by different models. Inkling is the most exciting model launch we've seen from an America…

Yea, that's an interesting result as well. The Terra apps don't feel 35% less feature-rich. So it seems quite token efficient.

Similarly, we updated our model arena (52 apps each built by 26 models) to have GPT 5.6 Sol, Terra, and Luna today: https://arena.logic.inc/ It's really interesting to see the Sol/…

Awesome - will work on getting those in.

If you like this kind of comparison, we have an arena of 52 apps one-shotted across 21 models here: https://arena.logic.inc/ I keep it pretty up to date (tomorrow Grok 4.5 and Sonn…

Hi HN, we share a ton of agent skills at my startup¹ and keeping them in sync was a pain, especially the full cross-product of every team member and every agent they use. We built …

Yep, 100% correct. We're still reviewing and advising on test cases. We also write a PRD beforehand (with the LLM interviewing us!) so the scope and expectations tend to be fairly …

It doesn't require removing them if you think you'll need them. It just requires writing tests for those edge cases so you have confidence that the code will work correctly if/when…

FWIW all of the content on our eng blog is good ol' cage-free grass-fed human-written content. (If the analogy, in the first paragraph, of a Roomba dragging poop around the house d…

I suspect it will still fall on humans (with machine assistance?) to move the field forward and innovate, but in terms of training an LLM on genuinely new concepts, they tend to be…

I never claim that 100% coverage has anything to do with code breaking. The only claim made is that anything less than 100% does guarantee that some piece of code is not automatica…

Can you say more? I see a lot of teams struggling with getting AI to work for them. A lot of folks expect it to be a little more magical and "free" than it actually is. So this pos…

Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite ste…