lamroger

Wanted to hack today but the universe is telling me to go enjoy the sun

Reminder that vets have it extra hard.

And a reminder to myself to do good.

really enjoyed this too

Wild

Thanks for sharing - incredibly inspirational on a personal and professional level

I'd order pizza from that site

Sorry - don't have actual advice. I remember the developer relations community being inclusive. Maybe you can DM some of them for specific advice or just someone to talk to. https://twitter.com/mipsytipsy comes to mind. Hope it isn't bad form to suggest someone on their behalf but comes from respect.

it's sad how many places are only staffing with senior+ engineers.

No thanks

Looks fun!

I thought llama is open weights and open to commercial with reasonable restrictions. I haven't heard practitioners who fine tune llama having trouble with it

interesting though. when will these robots be walking ads like instacart pivoted to. side hustle selling data to ai companies. it's all from public spaces so no one to argue copyright. i'm in LA and the robots are pretty freaking annoying. They take up the whole block. race towards you and slam on the breaks. also can we ban the scooter litter?

data science is more = to statistics

I feel like modern ML is finding out that you can apply the chain rule to calculate derivatives cost effectively and then scaling up a really really really big equation to then iteratively converge on the answer you want.

Agreed! I think it's going to be hard for software developers to adjust to the "data science/engineering" mindset of monitoring and iterating on the long tail of maintenance. A lot of teams already have this issue with deterministic code running in production. I think there's a big opportunity to help purely software teams to learn and adjust.

Still incredible in 2023. Goes to show UX and maybe first to market will be the differentiator

What is it called when people label themselves as something but aren't that thing? People gotta walk the walk

I am - Great for solo dev-ing.

thanks for the rec

low 7 figures after how long?

for sure but going from 90% to 95% might be worth for some

``` When to use fine-tuning:

Fine-tuning GPT models can make them better for specific applications, but it requires a careful investment of time and effort. We recommend first attempting to get good results with prompt engineering, prompt chaining (breaking complex tasks into multiple prompts), and function calling, with the key reasons being: * There are many tasks for which our models may initially appear to not perform well at, but with better prompting we can achieve much better results and potentially not need to be fine-tune * Iterating over prompts and other tactics has a much faster feedback loop than iterating with fine-tuning, which requires creating datasets and running training jobs * In cases where fine-tuning is still necessary, initial prompt engineering work is not wasted - we typically see best results when using a good prompt in the fine-tuning data (or combining prompt chaining / tool use with fine-tuning) ```

my bad - Fine-tuning for GPT-3.5 Turbo is now available, with fine-tuning for GPT-4 coming this fall.

Support for fine-tuning with function calling and gpt-3.5-turbo-16k will be coming later this fall.

i didn't catch that but getting consistency is probably worth it in most cases. depends on your budget

gotta wait til fall for general availability of fine tuning? looks like there's a legacy version too?

openai is streets ahead

And does it matter what other people think?

+1 on "stop doing things that aren't working, work for someone else for a while, get some money, recover, learn why you are not being successful building your businesses, and maybe try again...? "

We're rooting for you!

Thanks for sharing! Diagrams look great from a first glance. Will read more indepth later!

I'll give it a shot and keep that in mind

Interesting - If I'm running a "single" chain, do you know if langsmith would be helpful? Deployment solutions would be interesting - things are so new it would be hard to choose so my default would be just to wrap the API and keep it simple.

Very cool!