rtaylorgarlock

Cool product :) I'm still so gun-shy on using any llm tooling in prod for sysadmin, devops, etc. but frontier models walk circles around me in bash at insane tok/s. cURL and cat + json sounds nice

Also possible to find the 'Speculoos' spice mix for further recipes :)

Uhoh, looks like some party-line voters have HN accounts

Wise to critique both holistically, which makes it funny when people want to ignore an individual's or group's track record (especially regarding specific mental models or types of analyses) when evaluating a specific argument

Happy OPNsense user here, with no current plans to change. Ruckus unleashed + brocade ICX treat me very well. The all-in-one router indeed are only access points to me, and I don't exactly wish 'only having an AIO router' on people.

party-line voters would be really mad if they could read this

Oh don't worry, you get to keep your higher usage allowance for one month. hahahaha

Pretty sure this is the reason HN exists ¯\_(ツ)_/¯ lol

Interesting; I checked my personal acct setting this morning given other news, and found it disabled. I hadn't used my chatgpt account since ~'23 or earlier, and it was retained since then.

"hacker news"

Heads up, I've universally been downvoted here for humor. Telling, really.

I've been a bit more careful about complaining about regulations broadly due to competitive advantage, e.g. ITAR

Yet: how is pricing? Evaluating contents and routing appropriately isn't a new challenge in OCR, one of the oldest fields of applications in ML. Thus, how do the smaller open models perform in tandem with relatively pricy $/pg models & APIs? Your use case is remarkably rare relative to the volume and price sensitivity of enterprise data warehouse ops.

Let those be the 40% we prefer less :) Revealing stack does not validate the framework, but we appreciate some foss sauce 'round these parts.