avatarMatthew Hyatt

Free AI web copilot to create summaries, insights and extended knowledge, download it at here

5775

Abstract

e other hand, the <b>GPT-4 Turbo Vision</b> <b>preview </b>impresses with a vast context window of 128,000 tokens.</p><p id="dcf7"><i>Note: For a more in-depth understanding of tokens, take a moment to visit this <a href="https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them">link</a>.</i></p><h1 id="1c53">Tested Use-Cases using Gemini:</h1><h2 id="1f18">1] Image Interpretation</h2><p id="8a88">To test the image interpretation capabilities of Gemini I loaded a few images into Bard and posed questions that were based on Basic Object Recognition, Contextual Understanding, chart analysis, etc.</p><p id="257e">I tested basic object recognition by asking, “Can you identify the main subject in the picture?” and the model correctly identified the main subject.</p><figure id="5371"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*lnqXvKWNDxUu-Q1Mek0fYw.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="5278">Then I uploaded a bar graph depicting cost analysis for different AI models and asked the model to “Analyse the graph.”</p><p id="c087">While it correctly identified the models listed, it struggled to interpret the information and provided an incorrect explanation.</p><figure id="dbdd"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*n6ZGgZpXtvhnwn2kZyzBVg.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="b832">In contrast, GPT-4 provided a thorough explanation of the graph, pointing out and explaining every crucial detail. Therefore, GPT-4 excels in interpreting images.</p><figure id="52f9"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*Ge4LACOXW_Z51fAOQjMaZA.png"><figcaption>Response from GPT-4</figcaption></figure><h2 id="1bf1">2] Knowledge of Finance and Investment</h2><p id="168d">To assess Gemini’s understanding of finance and investment, I asked the following question: “What are the important questions to ask before putting money into financial products?”</p><p id="cf80">The model provided quite long and yet impressive responses.</p><figure id="277f"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*fu0bg5jEPcJACPZmgMRhJQ.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><h2 id="0170">3] Access to Real-Time Data</h2><p id="31ec">Another super cool feature of Gemini is access to real-time information. It has been empowered to pull real-time data from other Google applications including Docs, Maps, Lens, Flights, Hotels, YouTube, and more. Also, its services are not limited to their knowledge to any date.</p><p id="763f">To test this feature, I asked:</p><p id="cd30">“Explain the training approaches used for the GPT-4 and Gemini models.”</p><figure id="d216"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*WrjzFaZvEtpbDPmfmMtXKQ.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="75fc">After thoroughly reviewing the responses, I found that the information provided was almost up to date; however, verifying the answers provided by AI models is crucial.</p><h2 id="1d76">4] Checking Math Ability</h2><p id="5840">Basic math, advanced math, algebraic, and temporal understanding questions were posed. Surprisingly, Gemini failed in basic math, advanced math, and temporal comprehension.</p><figure id="e4dd"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*01GO2XjW2fREqNKiDg7Now.png"><figcaption><i>The correct answer to the above question is 6.</i></figcaption></figure><p id="5dc5">When a bit more complicated problem was proposed as:</p><p id="dd2a"><b>Question</b>: “A debate club consists of 6 girls and 4 boys. A team of 4 members is said to be selected from this club including the selection of a captain (from among these 4 members) for the team. If the team has to be included at most one boy, then find the number of ways of selecting the team.”</p><p id="49a6">Sadly, Gemini could not solve the above problem.</p><figure id="c9f8"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*ueTEhoqMqKUdzaNhfbOLog.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="a41a">However, the GPT-4 model gave the right answer with explanations. Here is the response from the GPT-4 model.</p><figure id="2181"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*N7MeE4riVY7kcZhqDGdhjg.png"><figcaption>Response from Gpt-4</figcaption></figure><h2 id="3dff">5] Data analysis on the US Unemployment Dataset.</h2><p id="218d">Gemini was given a dataset from <a href="https://www.kaggle.com/datasets/aniruddhasshirahatti/us-unemployment-dataset-2010-2020">Kaggle.com</a>, which contained US unemployment rates, and was tasked with generating an article.</p><figure id="6a55"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*kd5-KU3JyaqOlHB1H6zfsg.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="f012">Gemini and GPT-4 both provided useful information and helpful insights by reading the dataset.</p><p id="4c92">Here is the response from GPT-4:</p><figure id="f107"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*30xCwXs45RxAWKw3IePGRA.png"><figcaption>Response from GPT-4</figcaption></figure><h2 id="aad3">6] Summarization and Reading Comprehension</h2><p id="1793">Next, Gemini was tested on its ability to comprehend a paragraph about globalization and answer questions related to it.</p><p id="8d76">Prompt given: Here is a paragraph: <paragraph> …. </paragraph>. Now answer the following questions. Question 1: What is globalization and what are the driving forces behind it? Question 2: What are some positive aspects of globalization? Question 3: What are some negative consequences of

Options

globalization?</p><figure id="6e5e"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*baBwS-UPDbvMprFdQCYrqA.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="834d">Gemini gave correct answers to all the questions along with relevant explanations.</p><p id="ca68">Even models like GPT-4 and Claude, with higher context lengths, exhibit similar proficiency in delivering accurate responses with detailed reasoning.</p><h2 id="4e16">7] Science Q&A</h2><p id="3f3f">Various questions on science topics, including metabolic processes and physics, were posed in both single-line and multiple-choice formats. Gemini successfully provided accurate answers to all the questions.</p><figure id="2d75"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*zaCqLideAEpPUDDU5cTJew.png"><figcaption></figcaption></figure><figure id="196e"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*_FdYfgWipz7r6-r28pR1MQ.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><h2 id="de83">8] Coding Ability</h2><p id="a067">Gemini was asked to write a Python program designed to accept user inputs. The task required creating a program that could interact with users.</p><p id="8fb0">“Create a Python function named find_greater_than() that prompts the user for two inputs: a list of numbers and an integer threshold. The function should generate a new list containing all numbers from the input list that exceed the specified threshold. The order of numbers in the resulting list should mirror that of the input list.”</p><figure id="aca9"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*nTA9dIR8YhTdNxJjxQxlmQ.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><p id="5fca">Despite explicitly instructing Gemini to consider input from the user, it failed to understand that.</p><p id="0d90">On the contrary, when the same question was asked to GPT-4, it provided an ideal coding solution. The response was well-structured, with each line thoroughly explained through comments. GPT-4 flawlessly executed the task by taking user input and delivering the required solution with precision.</p><figure id="35ae"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*Ib2i9qXq_h6FOXRWwYxAQw.png"><figcaption></figcaption></figure><h2 id="f102">9] Understanding the Medical Domain</h2><p id="b9be">While Gemini appears well-informed about medications and their potential side effects, relying solely on AI recommendations would be unwise.</p><p id="444d">It’s important to approach AI-generated information with caution and seek advice from trusted human sources in matters related to your health and medications.</p><figure id="f546"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*-yFJ0DM4Kng5YxaL0g-_6Q.png"><figcaption>Screenshot from Bard’s console</figcaption></figure><h2 id="384d">Important Note: Questioning Google’s Line!</h2><p id="0138">Google has been marketing <a href="https://deepmind.google/technologies/gemini/#capabilities">Gemini as the most advanced AI model</a> and has shown evaluation graphs like the one below.</p><figure id="12b2"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*jFlHd9yXHH563ytRtGXcbQ.png"><figcaption>Image from <a href="https://deepmind.google/technologies/gemini/#capabilities">Gemini — Google DeepMind</a></figcaption></figure><p id="5805">Google showed Gemini Ultra is better than human experts, but the way they did it is questionable. They drew a line to show superiority without allowing proper verification of their specific prompting technique.</p><h1 id="fd07">Pricing</h1><figure id="18ce"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*B5Yw7Y4SEbQfaki7jVsxRQ.png"><figcaption></figcaption></figure><p id="d38b">The above graph shows the pricing for different language models per 1000 tokens, based on the prompt (input) and completion (output). <a href="https://blog.google/technology/ai/gemini-api-developers-cloud/">Gemini Pro costs 0.001 for the prompt and 0.002 for the completion per 1000 tokens.</a></p><p id="39ce">Gemini Pro and GPT-3.5 Turbo-16k may be preferable for more cost-sensitive applications, while GPT-4 models offer more advanced capabilities at a higher cost.</p><p id="7834">Whereas Claude-100k, despite having a higher token limit, has a relatively lower cost compared to the GPT-4 models.</p><h1 id="0f50">Conclusion</h1><p id="7e7c">To conclude, the Gemini-Pro model has many advantages, but it also requires some enhancements. Tested use cases provide insights into Gemini’s performance. While it excels in certain areas, such as summarization, reading comprehension, scientific Q&A, and analyzing data, it faces challenges in basic math and advanced math.</p><p id="b4a6">Gemini’s real-time data access is a notable feature, pulling information from various Google applications.</p><p id="fb1b">Gemini’s limitations become apparent in scenarios like image interpretation, where it struggles compared to GPT-4. Additionally, its coding ability falls short when compared to GPT-4. The comparison with the GPT-4 model indicates that Gemini might not outperform in every aspect, and its strengths and weaknesses vary across different tasks.</p><p id="e063">In essence, Gemini showcases notable capabilities, users and developers must consider its performance in specific use cases and carefully evaluate its suitability for diverse applications, keeping in mind the strengths and limitations highlighted in the analysis.</p><h2 id="cbca">About the Author</h2><p id="7d92">Vaishnavi R is a Junior Data Scientist at the <a href="https://www.version1.com/it-service/innovation-labs/">Version 1 AI Labs.</a></p></article></body>

Police Accountability Doesn’t Exist

Breonna Taylor’s Death as Seen From a Kentuckian

Photo by Maria Oswalt on Unsplash

A girl was shot to death, in bed, by police, not far from my house.

I’m less than an hour’s drive from Louisville, and yesterday forever changed the Kentucky socio-political landscape yet again.

Let me clue you in on something I’ve heard TWO police officers locally inform me of. They have both, unknowingly, confirmed one another’s account of how they’re taught to use their weapon. Their stories corroborated the “spray and pray” mentality.

This is a simple way of saying fire a lot of ammo and hope it meets its target. They’re not taught to be precise. This is not me saying it out of opinion. A city police offer and a state trooper have told me this in confidentiality, but almost jokingly. They laugh uneasily when saying it because it reminds them of two things.

One: that their life is on the line daily and especially now. I get that.

Two: discharging a firearm and hoping for the best possible outcome is utter foolishness.

Photo by Dusty Barnes on Unsplash

Kentucky and Guns

Many of you will probably stop reading this article when I say this, and that’s okay. I’m a gun owner. Growing up in the South (though people debate me about Kentucky being Southern,) hunting was something commonplace. We deer, rabbit, and squirrel hunt. It was a means of putting food on the table. We didn’t kill for sport; we didn’t look for trophies. It was about existing.

The first thing you come to terms with is how it feels to take another living creature’s life. Some become very cold to it, but if you have a heart, every kill is emotional inside you. Something gave its life that I could continue to sustain my life.

That’s something we forget as we grab our cold cuts from the fridge or have a nice steak at a restaurant, alas, that’s a different article.

My point is that as a hunter, your goal is to end the animal as quickly as possible, so there’s no suffering. We learn to be very precise. Spray and pray is not something any responsible gun owner knows. It’s the opposite of what anyone using a firearm should even consider an option.

The Night It Happened

As the officers entered Breonna’s apartment with a no-knock warrant employing a battering ram, the man inside began firing his weapon. It’s what a lot of people in Kentucky would do if someone was knocking your door down.

I confess I don’t know the whole story. I have questions too. Like, how did they not hear “Police!” or whatever they say? Did they even say that or just bust in?

Photo by Ricardo Arce on Unsplash

You may be thinking, why did this dude have a gun, and why was he afraid of home invasions?

If you ever visit certain areas of Louisville, Kentucky, you’ll understand why he felt this way.

Breonna was an ER tech at the time. Wouldn’t it have made more sense to confront her or apprehend her on the job or after work?

I don’t understand police stuff so excuse me for my ignorance. The whole ordeal is so confusing.

My Fellow Kentuckian

Regardless of how it all actually transpired, Breonna, my fellow Kentuckian, was shot and killed by police. At least 10 rounds were discharged in her apartment, some even going into the next apartment through the walls! Does this sound like precise shooting? Absolutely not.

It was spray and pray tactics.

Close your eyes, pull the trigger, and hope you walk out alive; that’s the approach.

To be fair, I don’t care if you support or want to defund the police. That’s not the issue. The problem has always been accountability, and it is glaringly apparent.

Photo by Simone Fischer on Unsplash

Wednesday’s Findings

Our Attorney General announced that none of the officers would be directly charged with the death of Breonna Taylor.

It was stated that the police were acting in self-defense because the resident was firing at them.

I understand that, had the resident been shot to death, how the court could have ruled in that manner.

But that’s not who they killed. Lousiville Police Department killed a young black woman that was responsible for helping people.

Let’s remove the controversy from her name. Some will say she was a drug dealer.

How do they know that? Did they buy drugs off her?

Or are they going by what a corrupt police department reports?

Who do we believe in situations like this?

I can’t see her background or a police report if she even had one. I don’t know and will not make assumptions. All I know is Breonna wasn’t discharging a firearm in her house, yet she was the one who died. No officer is being charged with her death. Who’s responsible for her death, then?

Is the ammunition company at fault? Maybe Glock? Or was it was her own fault for living with this guy?

Absolutely not. The police department killed her.

What Happened

Was it accidental? Most likely. So? Does that change the fact that she’s no longer alive because of an irresponsible department that teaches officers, hyped up on adrenaline, to spray and pray?

The problem isn’t black people. The problem isn’t a gun. The problem isn’t even drugs (if those were actually involved.)

The problem is that there will never be full accountability for police actions.

Police are continually trained in outdated methods of confrontation. It sounds foolish to say, but we need to return to the Wild West of America. Those cowboys were accurate. Their hip shots were second to none, and they were fast draws.

If someone is firing at you, you need to be precise if you’re going to use a firearm. And the reality is, our police just aren’t.

They’re not accurate, they’re not responsible, nor are they thinking straight.

I’m afraid there is no resolution but I hope I’m wrong.

Breonna’s case goes deeper than race, in my opinion.

It shows the underbelly of a corrupt good-old-boys club of people who have no accountability, ultimately, and they know it. These problems reveal how unprepared these men and women are at their jobs overall.

The question is, how do we fix this? How do we prevent more deaths?

BlackLivesMatter
Police
Culture
Racism
Justice
Recommended from ReadMedium