AI Valley
Posts
🐶 How to use LLMs as your personal research assistant

🐶 How to use LLMs as your personal research assistant

PLUS: Amazon has launched Amazon Q

Mr Barsee
02 May

Together with

_{Sign up}_|_{Follow us on X}_|_Sponsor

Howdy, happy Thursday, AI family! 🐶

🧵 Here’s some useful AI news and tools I gathered today:

💡 How to use LLMs as your research assistant
🤌 14 Cool AI/Tech updates
🔍️ + new AI Tools, Resources, and other news

Ready, Set, Go: Today’s read should be about a 3.5-minute read.

AI GUIDE

💡 How to use LLMs as your research assistant

The first and most important rule is this:

Never ask an LLM for information you can't validate yourself or to do a task that you can't verify has been completed correctly.

The one exception is when it's not a crucial task. For instance, asking an LLM for apartment decorating ideas is fine.

Bad: "Using literature review best practices, summarize the research on breast cancer over the last ten years."

This is a bad request because you can't directly check if it's summarized the literature correctly.

Better: "Give me a list of the top review articles on breast cancer research from the last 10 years."

This is better because you can verify that the sources exist and vet them yourself, and of course, they are authored by human experts.

TIPS FOR WRITING PROMPTS:

It's pretty easy to ask an LLM to write code or find relevant information for you, but the quality of the responses can vary widely. Luckily, there are things you can do to improve the quality.

SET THE CONTEXT:

Tell the LLM explicitly what information it should be using
Use terminology and notation that biases the LLM towards the right context

If you have thoughts about how to approach a request, tell the LLM to use that approach.

"Solve this inequality."

"Solve this inequality using the Cauchy-Schwarz theorem, followed by an application of completing the square."

These models are much more advanced in language than we might think.

Even extremely vague guidelines can be helpful.

BE SPECIFIC:

This isn't Google. You don't have to worry about whether there's a website that discusses your exact problem.

"How do I solve a simultaneous equation involving quadratic terms?"

"Solve x=(1/2)(a+b) and y= (1/3) (a^2+ab+b^2 for a and b" for a and b"

DEFINE YOUR OUTPUT FORMAT:

Take advantage of the flexibility of LLMs to format the output in the way that's best for you, such as:

Code
Mathematical formulas
An essay
A tutorial
Bullet points

You can even ask for code that generates:

Tables
Plots
Diagrams

Once you have the output of an LLM, that is only the beginning.

YOU NEED TO VALIDATE THE RESPONSE.

This includes:

Finding inconsistencies
Googling terminology in the response to get supporting sources
Where possible, generate code to test the claims yourself

LLMs often make weird mistakes that are inconsistent with their seeming level of expertise.

For instance, an LLM might mention an extremely advanced mathematical concept yet fumble over simple algebra.

This is why you need to CHECK EVERYTHING.

USE THE ERRORS TO GENERATE FEEDBACK:

If you see an error or inconsistency in the response, ask the LLM to explain it
If the LLM generates code with bugs, cut and paste the error messages into the LLM window and ask for a fix

ASK MORE THAN ONCE:

LLMs are random. Sometimes simply starting a new window and asking your question again can give you a better answer.

USE MORE THAN ONE LLM.

I currently use Bing AI, GPT-4, GPT-3.5, and Bard AI, depending on my needs. They have different strengths and weaknesses.

In my experience, it's good to ask GPT-4 and Bard AI the same math questions to get different perspectives.

Bing AI is good for web searches. GPT-4 is significantly smarter than GPT-3.5 (like a student at the 90th percentile vs. the 10th percentile) but harder to access (for now).

REFERENCES

References are an especially weak point for LLMs. Sometimes, the references an LLM gives you exist, and sometimes they don't.

The fake references aren't completely useless. In my experience, the words in the fake references are usually related to real terms and researchers in the relevant field. So googling these terms can often get you closer to the information you're looking for.

Additionally, Bing AI is designed to find web-references, so it's also a good option when hunting for sources.

PRODUCTIVITY

There are a lot of unrealistic claims that LLMs can make you 10x or even 100x more productive. In my experience, that kind of speedup only makes sense in cases where none of the work is being double-checked, which would be irresponsible for me as an academic.

However, specific areas where LLMs have been a big improvement in my academic workflow are:

Prototyping ideas
Identifying dead-end ideas
Google searches

One final word of advice: Be careful not to get sucked into side projects. The sudden increase in productivity from these tools can be intoxicating and can lead to a loss of focus.

TOGETHER WITH MIXO

🤖 AI-powered platform helps launch websites and startups in seconds

Traditional website builders often promise simplicity, but making a sleek, professional website can be far trickier than expected. Navigating through design choices and dealing with complex code can be daunting.

But with AI platforms like Mixo, with just a simple prompt you can create an impressively professional multi-page website in seconds.

What's more, editing the design and content is straightforward with the help of the integrated AI editor.

This smart tech manages not just the content and structure of your website but also oversees customer subscriptions, SEO, and more, saving you time and leaving you to focus on launching your business idea.

Try ithere

Curated updates

OpenAI just updated its website. It looks pretty good.
Amazon has launched Amazon Q, a generative AI assistant designed for developers and businesses.
An internal email revealed that Microsoft invested in OpenAI partly because it was “very, very worried” about falling behind Google.
Open Gemini anywhere in Chrome by typing “@”. It’s that easy.
AI video throwdown: OpenAI’s Sora vs. Runway and Pika.
Google just announced Med-Gemini for medical tasks. It beats GPT-4 on all benchmarks.
Yelp is launching an AI chatbot to help consumers connect with relevant businesses. The chatbot uses OpenAI's LLMs and Yelp's data to understand user problems and provide relevant professional suggestions.
Crypto is back. Stripe will start supporting global stablecoin payments this summer. Transactions instantly settle on-chain and automatically convert to fiat.
Reviews of both The Humane AI Pin and Teenage Engineering’s Rabbit R1 are not positive.
Airbnb Dives Into Pop Culture With New Home and Experiences Category Called ‘Icons’.
Anthropic launches Claude 3 AI-powered iPhone app to compete with ChatGPT.
Eight newspapers owned by Alden Global Capital’s MediaNews Group are reportedly suing Microsoft and OpenAI, alleging that the tech companies used the newspapers’ content to train artificial intelligence (AI) models.
Pinterest says its AI-powered collages are now more engaging than Pins.
ByteDance releases Hyper-SD! This brings high-quality image generation with Stable Diffusion down to a single inference step.