Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Did Google kill its enterprise workhorse model?

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 22 posts

Re: Ask HN: Did Google kill its enterprise workhorse model?

#12

Post by waldrews »

ernsheong wrote: post #6

Flash is the new Pro, try it first

We sure did. It's a great writer, better in a harness, will process lots large context, but complex reasoning with convoluted rules and low hallucination tolerance? That's still larger model territory.

Re: Ask HN: Did Google kill its enterprise workhorse model?

#13

Post by waldrews »

OutOfHere wrote: post #10

As an alternative, it's not a bad idea to first convert each document to markdown via a thinking or agentic LLM. Embedded figures can even be embedded as readable tables or Latex or Mermaid. Do record the name and parameters of the model that performs the conversion. You can then query the markdown using any model with an input token cost that is exactly equal to the encoding of the markdown. For multiple queries you…

Yup, tried all variations of that. There's the advantage that you can use a lower hallucination OCR specific model for the pre-processing, at least for clean text. But for something hard like handwritten forms, applying VLM with context is less error prone than preprocessing to text.

Also - and this is bizarre - the token cost of doing that is higher, not lower, at least in Gemini world, and by a large margin. That's very counterintuitive, but a page encoded as image tokens can be smaller than same page as text, and is not meaningfully lossy on documents that are just typed text because the models are well trained on those.

Re: Ask HN: Did Google kill its enterprise workhorse model?

#14

Post by ernsheong »

waldrews wrote: post #12
ernsheong wrote: post #6

Flash is the new Pro, try it first

We sure did. It's a great writer, better in a harness, will process lots large context, but complex reasoning with convoluted rules and low hallucination tolerance? That's still larger model territory.

There's still 3.1 Pro though, as ancient as it sounds now

Re: Ask HN: Did Google kill its enterprise workhorse model?

#15

Post by waldrews »

ernsheong wrote: post #14
waldrews wrote: post #12

Earlier quoted context omitted.

We sure did. It's a great writer, better in a harness, will process lots large context, but complex reasoning with convoluted rules and low hallucination tolerance? That's still larger model territory.

There's still 3.1 Pro though, as ancient as it sounds now

Yup. The problem is that it's bizarrely still not in General Availability status.

Re: Ask HN: Did Google kill its enterprise workhorse model?

#17

Post by trio8453 »

PaulShin wrote: post #11

Google is falling behind in this competition.

And it's mostly from lacking vision and a clear direction, not from being behind on research or engineering. For example, Gemini 3.8 Flash is really impressive.

But their whole model product line is confusing, even the version numbering barely makes sense. They're barely selling agentic coding or the Gemini chat, the fumbled the coding harness race with the weird Gemini CLI / Antigravity rebrand - the whole thing is a mess.

Re: Ask HN: Did Google kill its enterprise workhorse model?

#19

Post by ernsheong »

waldrews wrote: post #12
ernsheong wrote: post #6

Flash is the new Pro, try it first

We sure did. It's a great writer, better in a harness, will process lots large context, but complex reasoning with convoluted rules and low hallucination tolerance? That's still larger model territory.

sounds like you might need to beef up your harness first, and run multi-agent verification loops
Post reply on HN