Viewing profile — m00x

This is where MoEs shine though. You don't need all experts in memory at once. Diffusion inference doesn't have sparse inference.

Agentic coding is absolutely not a failure. It's just not the 10x that CEOs really wanted it to be. We learned that some tasks don't really benefit from AI while others do. My team…

By what he's saying he clearly isn't.

I've interviewed a ton of junior engineers. Our company was senior-heavy and we're just now diversifying. 80% of them should reconsider their career paths. They glaringly cheat dur…

Youtube should consider their engineers responsible for the software they write. Big companies these days are just bureaucracy tricks and politics. There's a small handful of real …

If you're calculating stock gains, taxes, etc. You'll want to do it on BigDecimal on line items, then sum it up. Cents could lose precision leading to a large difference on million…

Hyphens here are meant to be formatting. You would be correct if this was a literary piece, but handbooks and sheets don't need to use these rules.

It's a good indicator but absolutely no guarantee. I've had to tell project managers this because they didn't understand this concept.

BigDecimal should be used by almost everyone except for HFT since they're really slow.

You can't do everything you need with an integer. There are values you might want to display or calculate with that are smaller than cents. In some places you'll need things like B…

It could be a much bigger MoE model

On modern hardware a cow page copy should only take 1-5ms. Redis forks to save the db to disk and it's been a solid design choice. I guess it depends on how sensitive your applicat…

[flagged]

These LLM replies are really getting annoying.

Maybe it has to be fine-tuned per tool just like functiongemma

what are you talking about

Good artists get paid plenty. The hard part of art was always about either representing emotion, or a story. AI can't do that as it has no emotion, nor story.

> how you do one thing is how you do everything. That simply isn't true though. It's not even possible to be true. Will a neurosurgeon put as much time in their cooking/cleaning/et…

[flagged]

They are profitable to opex costs, but not capex costs with the current depreciation schedules, though those are now edging higher than expected.

That's GPT4 thinking. New models use tools to look at current events or latest versions, and rely very little on weight knowledge.

Mythos is basically this

It doesn't reveal that they have no clue of what they're talking about. They know that a good number of idiot CEOs will hear this and dictate their engineers spend more claude/code…

Minimax 2.7 is fine for most web stuff. It's slightly worse than Claude at backend, but works great for frontend. They're all slop when the complexity is higher than a mid-tech int…

Must be nice working on simple stuff.