OpenAI's GPT-4o-Mini - The Maxiest Mini Model?

In this video I take a look at OpenAI's newest model GPT-4o-Mini and how it stacks up compared to the offerings from Google and Anthropic.

For more tutorials on using LLMs and building Agents, check out my Patreon:

🕵️ Interested in building LLM Agents? Fill out the form below

👨‍💻Github:

⏱️Time Stamps:
00:00 Intro
00:25 OpenAI GPT-4o Mini Blog Post
01:57 Model Evaluation Scores
04:58 OpenAI GPT-4o Mini Superior Textual Intelligence and Multimodal Reasoning
06:49 OpenAI GPT-4o mini Built-in Safety Measures
07:07 The Instruction Hierarchy Paper
07:14 Twitter Posts on GPT-4o Mini Jailbreak
07:42 OpenAI GPT-4o mini Availability and Pricing
07:52 What's Next for OpenAI GPT-4o Mini
08:42 OpenAI GPT-4o Mini Demo

[unclecode]

In the last two years, I've worked extensively with Small Language Models, and recently they've improved significantly. This isn't due to a change in their size but to the availability of high quality synthetic data, enabled by Trillion Parameters Models. Large Language Models act as data compression tools. It seems We had to first generate a very large model to digest vast amounts of information from internet, then use it to create specific synthetic data to enhance small models.

I believe the future lies not in creating bigger models but in leveraging synthetic data to elevate Small Language Models. In a year, we might see Small Language Models outperform current Large Language Models in benchmarks, thanks to synthetic data. Initially, we needed to create large, often under-trained models, but now we can use them to generate synthetic data in any format we need. This allows for highly specialized small models that excel in specific tasks. This is how I see the future unfolding.

[micbab-vgmu]

Sam my first tests were possitive - a good model for data extraction and clearence + JSON function calling works great - and this price:) I am waiting to fine-tune this model:) - it will be a fun:)

[frag_it]

I am loving these tutorials I would like to see you do in depth on using vllm as an api point for serving llm using azure kubernates cluster it would be soo useful to the community as we can then use quantized models of llama3 70b with very cheap gpu to help serve applications. I would be just amazing for the community then you can use that to help make agents with lang graph tutorials bro I would love it

[TomGally]

Thank you for the very informative video! I learn a lot from all of your videos.

[henkhbit]

Love competition👍 btw: Gemini flash has 1 million tokens, audio and video inputs

[COLLINSSAKALA-jqze]

Just from using it. I think it's now available for all, I'm impressed 😮. It's excellent, though it can’t browse the web in real-time. Despite that, it will be very helpful, especially for summarizing content, rewriting resumes, and tailoring them for job applications. I've also noticed an improvement in coding capabilities compared to the older model. When I generated code for my resume, it did a great job.

[thenoblerot]

I really like Claude, but Haiku is not great at function calling.
Love to see iteration! Thanks, Sam!

[SLAM]

What will the inference cost be if someone needs to finetune the model?

[RyluRocky]

5:40 It isn’t 4.5 it’s 4O it’s called 4O because it’s omnimodal meaning all modalities they never claimed to increase its intelligence but rather it’s a structural shift from GPT4

[stevenkies]

So, do we call this the AI, Chabot, or LLM war?

[DeathHeadSoup]

I would find this interesting if it was actually competing against open source models that I can use locally but since it isn't I find it to be not even news worthy. It only gives users a price cut when we all should be asking the question of whether using AI SaaS products in your software stack is a good idea? If they release this model as a local use product then it will be news worthy.

[davidwipperfurth]

RE: open-source models: I worry these cheap corporate models aren't competing with one another as much as they are competing against decentralization.

[hqcart]

if you do a math, 0.15/mil is actually cheaper than running a local model, not to mention it's better than all open source.

[Dhtkna]

Perhaps 4o mini is actually a distillation of 4.5 and not 4o

[clapppo]

all these new models are utterly obsessed with formatting / organising everything as lists...

[arskas]

Who wants expensive systems or cloud services when we've these super cheap models

[hope]

🛑🛑!!Note!!🛑🛑: OpenAI created mini for their selfish purpose to neuter a GPT-4o Plus you in a timeout you bad child and drop you back to GPT-4o mini much like it did with GPT-4 when it would drop you back to GPT-3.5 aka Dory! Wtf? Fact check me please but that is what i am seeing now. I just timed out for the first time ever in GPT-4o and it dropped me back to GPT-4o mini and took away my upload option again Wtf? 🛑🛑