HNHacker News
TopNewBestAskShowJobs

FezzikTheGiant

76 karma · joined March 31, 2024

submissionscomments
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
Thanks. Very cool. Have you ever tried to implement a transformer from scratch? Like in the Attention is all you need paper? Can a first/second year college student do it
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
Thanks!! This is really cool
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
Interesting. Thanks for the response. Do you have any resources where I can educate myself about this? How did you learn what you know about LLMs?
FezzikTheGiant··on Show HN: I made an app to make meal planning easy
This is cool. Is there a mobile app?
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
This might be asking for too much but is there a guide that explains each part of this process? Your comment made the higher level way clearer for me and I'd like to go into the weeds a bit on each of these
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
Thanks for the insightful response. This is exactly the type of answer I was looking for. What's the best way to educate myself on the end-to-end process of deploying a production grade model smartly in a cost efficient manner?
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
This is really helpful. I'm really new to this, what's the best way to educate myself on fine-tuning and deploying a LLM in the most cost and time efficient way?
FezzikTheGiant··on Ask HN: How does deploying a fine-tuned model work
Appreciate the response. Definitely gonna check it out. How is pricing structured
FezzikTheGiant··on Senate passes reauthorization of key US surveillance program after midnight
Hey, I replied to your comment about building an open source version of Aqua Voice. Emailed you about it too. Let me know your thoughts.
FezzikTheGiant··on A list of AI coding tools
I'm thinking of building something like this over the summer, an open-source alternative that is integrated into desktop with a community effort on building a training data source.

However the biggest concern is that it would cost a lot of money to build this. If you have any thoughts/advice I'd be happy to chat.

FezzikTheGiant··on Ask HN: How do I learn more about LLMs and ML?
Perfect. I have my own finals in a couple weeks haha, planning to look more into this and possibly build a project over the summer. 3B1B's videos sound like a good resource, and the nano-GPT videos look really useful too. I'll share what I come across as well!
FezzikTheGiant··on A list of AI coding tools
What valuable differences would an open source version have over aquavoice? Why do you need an open source version?
FezzikTheGiant··on Ask HN: How do I learn more about LLMs and ML?
Is this all the math that is required? If I know how to do basic linalg is that about what I need to know to be able to understand how LLMs work? My goal right now is to build stuff on top of LLMs
FezzikTheGiant··on Ask HN: How do I learn more about LLMs and ML?
I'm in the exact same situation as you rn. Freshman year of college and really interested in LLMs. Did you decide how you're gonna go about it? Maybe we could share resources
FezzikTheGiant··on Ask HN: How do I learn more about LLMs and ML?
I'm in the exact same situation as the poster rn. Freshman year of college and really interested in LLMs. I'm planning to take ML/Deep learning courses at my school later on, but in the meantime, what would be the best way to learn how to drive the car without exactly knowing how the engine works? What I mean is I want to learn how to fine-tune and build useful apps on top of LLMs
FezzikTheGiant··on Ask HN: How do I learn more about LLMs and ML?
How should I go about building one?
FezzikTheGiant··on Ask HN: Recommendations for Local LLMs in 2024: Private and Offline?
what about hosting? how would you recommend doing that
FezzikTheGiant··on Ask HN: Recommendations for Local LLMs in 2024: Private and Offline?
Thanks for the info! Appreciate it
FezzikTheGiant··on Ask HN: Recommendations for Local LLMs in 2024: Private and Offline?
So I can run local LLMs on my apple M1 air?
FezzikTheGiant··on Ask HN: Recommendations for Local LLMs in 2024: Private and Offline?
I asked this another place in this thread, but curious to know how you plan to run and deploy this model. What's the cheapest or I guess most cost efficient way to do this without burning money. I'm a college student for reference so I don't have a lot of money lying around to experiment.
FezzikTheGiant··on Ask HN: Recommendations for Local LLMs in 2024: Private and Offline?
What's the cheapest way to run and deploy a fine-tuned model today? If I understand correctly I'll need to run cloud GPUs right
FezzikTheGiant··on Ask HN: Most efficient way to fine-tune an LLM in 2024?
I was just gonna ask this question and saw this at the top of Ask. Interested.
FezzikTheGiant··on Show HN: I've built a locally running Perplexity clone
Thanks! As a CS student interested in learning more about this space how do you recommend I get started? I'm pretty early in my education so I kind of want to learn how to drive the car for now and learn how the engine works more formally later, if you know what I mean.
FezzikTheGiant··on Show HN: I've built a locally running Perplexity clone
look forward to it. this is really cool
FezzikTheGiant··on Show HN: Plandex – an AI coding engine for complex tasks
Appreciate the response. Really cool work!
FezzikTheGiant··on Show HN: Plandex – an AI coding engine for complex tasks
Curious to know how you built this. Is it GPT-4 or a fine-tuned model. How much does it cost?
FezzikTheGiant··on Show HN: I've built a locally running Perplexity clone
If you're open to it, it would be great if you could make a post explaining how you built this. Even if it's brief. Trying to learn more about this space and this looks pretty cool. And ofc, nice work!
FezzikTheGiant··on Launch HN: Aqua Voice (YC W24) – Voice-driven text editor
This is really cool. Does anyone who knows this stuff better explain how it works on the backend? The founders mentioned 6 different models but how do they interact with each other so fast? There’s definitely an LLM in the back interpreting the commands but how exactly does it work
FezzikTheGiant··on Show HN: Pagecord – Effortless blogging from your inbox
yeah that would be pretty cool.
FezzikTheGiant··on Show HN: Pagecord – Effortless blogging from your inbox
I think instead of building your own client for displaying the posts, if you linked it with substack/twitter and others it would be a useful tool.
← PreviousPage 2 of 3Next →