QA Wolf | AI lead / Multiple Roles | Remote (International) | Full-time | https://www.qawolf.com/
QA Wolf gets engineering teams to 80% automated E2E coverage fast, and keeps it there.
We are growing quickly and building the dream team of engineers to develop our test creation, running, and maintenance platform. The stack is Node.js, GraphQL, React, Prisma, Go, and Kubernetes.
We are looking for a master of AI engineering who stays familiar with the latest best practices and knows the trade-offs of different patterns.
You will own problems end-to-end: collect relevant details, spec and scope solution(s), communicate progress, ship and own the results.
You:
- love coding and want to work hard
- are a self-starter, curious, and ship projects undirected
- have a proven track record of delivering challenging technical projects
- have an eye for design and can make good judgement calls with ambiguity
- are an expert in one or more technical areas
- have meaningful contributions to open source projects
ntfy.sh for a wide range of things connected to git hooks or GitHub actions, since I use git for personal things - gives me a second pair of eyes on things asynchronously
Saw the title, jumped to the diagrams, and thought I knew where this was going, but I was way off. I made the exact opposite conclusion from a quick glance at the diagram - that debt gives you more freedom. It allows you to go in the red. That a safe, debt-free life leads to less volatility and therefore less ups. Then I read the article, and couldn't hold both opposing ideas in my head.
It answered "How many frogs does a horse have?" correctly, with perfect reasoning. No model I've tested has ever answered that correctly without 3-4 hints.
"A horse has one frog per hoof. The frog is a part of the horse's hoof, located on the underside, which acts like a shock absorber for the hoof, assisting with circulation and traction. Since horses have four hooves, they typically have four frogs, one in each hoof."
GPT4 seems to handle this fine, unless I'm confused?
GPT-4-turbo-2024-24-09 (temperature = 0.7) just told me a horse had one “frog” per hoof and went on to clarify that a frog does not refer to the amphibian but to a part of the horse’s hoof.
Gemini Pro (the current web chat version) gave a similar answer, either no frogs or four depending on the intended meaning, and showed a photo of a hoof. All 3 drafts agreed on this.
Other models I have tried said a horse had no frogs. That includes gemini-1.5-pro-api-0409-preview as provided by the Chatbot Arena (temperature = 0.7, 2 tries).
I mean, i just tested this prompted, and have no clue what side is correct lol?
How many frogs does a horse have?
Oh it appears
Model B: gpt2-chatbot
is correct?
A horse has one frog in each of its hooves, making a total of four frogs. The frog is a part of the horse's hoof, located on the underside. It is a V-shaped structure that helps to absorb shock, provides traction, and aids in the circulation of blood through the hoof. The health and shape of the frog are important for the overall well-being of the horse's feet.
If a glider shows up somewhere by accident, like in an an otherwise random-looking arrangement of floor or wall tiles in a bathroom or somewhere, then I'll certainly pick it out immediately (and be unwarrantedly cheerful for the next half hour or so). But that doesn't happen all that often.
It seems like I rarely have dreams about Life patterns, though it does happen. Maybe some people with better-resolution imaginations might have a different experience, but Life patterns need a lot of precision and focus, and in my dreams everything is always fluid and shifting and I can never find my car keys or my homework, let alone any interesting Life configurations.
I understand the intension and reference you're making. I bet the implementation of GPT-4 is probably something along those lines. However, spreading speculation in definitive language like that when the truth is unknown is dishonest, wouldn't you agree?
Sure, I could it put it less definitively, but realistically, what else can it be? The transformer won't change much and all of the models, at the core use it. It's a closely guarded secret because it's easy to replicate.
> The null hypothesis is that the subject has no ability to distinguish the teas
Since the hypothesis was invalidated, we can begin investigating _how_ she's able to distinguish it, which is what you're getting at.