its actually not that weird if you consider that those shopify engineers are probably not even exceeding 150,000 usd on average salary wise

canadian dollar is very cheap so you'd likely see 40~50% more headcounts for the same burn rates you get in USA

i definitely dont think those shopify engineers are going to be retained long term however

not sure why you are being downvoted, but that has been my experience with 3.7 flash and sol/fable comparisons

i think luna-max has the best cost value offer when it comes to coding, but i note the multi modality of gemini flash as a win

i might consider 3.8 flash for simple side hobby projects or quick scaffolding but would not trust it for long agentic tasks, that really is the realm of sol/fable

agy cli still has a lot of issues not sure if its due to the underlying model hallucinating or the harness or both

thats not just the context growing issue, hallucinations is a thing

I routinely have massive threads using Fable and if anything it only gets better and better over time

i find deepswe not very reliable for instance it puts grok 4.6 xhigh over sol medium

not really getting the excitement over this, its at opus 5 medium level, and opus 5 is not really the go to model , claude purists hate it

so its fast sure and decent at non coding usage but for developers nothing can really top sol or fable.

even grok 4.6 is so so and i would not choose 3.8 flash over it.

i discount people who lean too heavily into benchmark as the authoritative truth when it comes to evaluation of coding capability of these models.

experience tells me that those people simply have not used models for a long period of time specifically on coding and have run their own comparisons

to someone who uses all vendors, the differences are very palpable and drives purchase decisions.

also keep in mind Gemini and other labs have repeatedly done benchmaxxing, you must have your own benchmarks to evaluate these models.

Contrary to some confusion about whether firefox will keep mv2:

Yes they will. Also I predict that MV2 is going to be a major boon for firefox.

It has taken a long time to prove the value of firefox to the masses and I believe mv2 extensions in particular ublock origin will be what keeps people coming back to it

I've not touched chrome in decades. Firefox stands strong. I would donate but in EU that comes with tax issues.

this is potentially useful for me do you know if this can fully handle callkit?

a spammer is motivated by self-enrichment

AI agents are grounded on the user provided direction. If it doesn't work well then it naturally loses trust.

> If it doesn't work well then it naturally loses trust

Too late. If it doesn't work well then it has already naturally destroyed trust.

Looked this up and yikes, Gander's CTO Jeff Wood did work at Pornhub.