How To Do A Literature Review (STRESS-FREE!)

Claiming AI tools are used for 'filtering' and are present in 'all of these' steps. — Confidence Mismatch (45/100)

At 0:00

Says AI is in 'all of these' steps and 'filtering' — without naming a single tool or showing how. That's not a workflow, that's a wish list. 💀

Why this score: The speaker makes a broad claim about AI tools being used for filtering and present in 'all' steps of their mental workflow. However, no specific tools are named, nor is any demonstration provided at this point to back up the blanket statement. It's a confident assertion without immediate evidence.

Original quote: “So, we'll head over here and this is what I am doing in my mind every time I'm doing a literature review. First of all, finding literature, go and search, go and absorb that information. Then, I'm filtering it using AI tools. And by the way, there's AI tools in all of these, spoiler alert.”

Sources: AI hiring tools may be filtering out the best job applicants, How AI in Resume Screening Shapes Hiring Practices, The impact of algorithms for online content filtering or moderation

AI tools mean you don't have to read everything for an 'awesome' result — Loaded Language (45/100)

At 0:30

Using 'awesome' and 'proud of' to mask the actual labor required 🎭

Why this score: The speaker uses high-emotion adjectives to describe the output without addressing the potential loss of depth when skipping reading.

Original quote: “The great thing about AI tools is that you don't need to read everything and then at the end we come out with an awesome literature review that you are proud of.”

Filtering is for 'sanity' because reading everything is impossible — Confidence Mismatch (45/100)

At 1:54

Framing the inevitable chaos of research as a 'sanity' issue 💀

Why this score: It's a massive understatement to call the entire scope of academic literature 'sanity-checking'; it's just how research works.

Original quote: “Now, we're filtering it for really sanity reasons because we cannot literally read every single paper that's ever been published in a particular field.”

AI is a 'shortcut' for the heavy lifting of reading abstracts — Loaded Language (45/100)

At 2:14

Calling the core of research 'heavy lifting' to make AI look like a cheat code 🚩

Why this score: The term 'heavy lifting' is used to make the manual process sound burdensome, making the AI solution feel more like a relief than a tool.

Original quote: “In the past, you would read all of the abstracts, but now we can sort of shortcut some of that heavy lifting by using AI tools.”

Recommending NotebookLM as a shortcut for finding key findings — Confidence Mismatch (45/100)

At 3:26

Selling a shortcut as a solution without mentioning the risk of AI hallucinations 💀

Why this score: The speaker presents using NotebookLM to 'highlight all the stuff you need' as a simple task, but ignores the massive risk of AI misinterpreting academic nuance or hallucinating findings.

Original quote: “And the last thing you can use is notebook LM. You can put all of your references here. And then down here, you can say something like, "Oh, let me know of the key uh findings in these papers and the most important papers from a particular all of that stuff."”

Claiming deep understanding only comes from manual reading — No Frame (75/100)

At 4:10

Actually making a real point about the value of human cognition 🧠

Why this score: This is a grounded argument. It acknowledges that while tools help, the 'sixth sense' of expertise requires the cognitive heavy lifting of actual reading.

Original quote: “And one of them is to read a full paper and get the right information into our brain. So we can start building that sixth sense, that understanding of a research field that only comes from reading the research.”

Claims reading only 20-25% of papers is a valid starting point — Confidence Mismatch (45/100)

At 4:30

Trying to turn 'skimming' into a scientific strategy. 💀

Why this score: He's claiming a specific, arbitrary percentage is a 'great starting point' without explaining how that number was derived or why it's sufficient for actual research.

Original quote: “researcher and we're looking to read between about 20 and 25% of the actual papers we've bubbled up. That is going to give us a great uh starting point for understanding the literature.”

Finding gaps is 'easier than ever' using these tools — Confidence Mismatch (45/100)

At 6:57

Claiming it's 'easier than ever' is a massive reach without showing the actual difficulty of verifying a gap 🚩

Why this score: The speaker pivots from identifying data points to a sweeping claim about the ease of finding gaps. It's an unsubstantiated leap in confidence that ignores the actual intellectual heavy lifting required to prove a gap exists.

Original quote: “And if there is a genuine research gap, consensus will say gap. It's easier than ever to find a research gap.”

Using LLMs to generate research structures via 'thought explosions' — Loaded Language (45/100)

At 7:52

Calling it a 'thought explosion' makes a messy process sound like a feature instead of a risk 💀

Why this score: The speaker uses colorful, casual language to describe a process that is actually quite risky in academia. It frames the chaotic input of 'random thoughts' into an AI as a valid methodology, glossing over the need for rigorous logical structuring.

Original quote: “And I like to put it into chat GPT or whatever large language model you like. I like to say, okay, I've got a literature review. This is the structure.”

Advocating for a top-down approach to research structure — No Frame (75/100)

At 8:25

Just standard academic methodology. No tricks here, just a straight-up process 🟢

Why this score: This is a direct statement of their personal workflow. It's not trying to sell a miracle or hide behind vague terms; it's just explaining how they organize information from general to specific.

Original quote: “And I always work with literature reviews from the broad ideas down to the tiny ones. So, first of of all, you want”

Recommending Thesis AI as a shortcut to a finished review — Plain Sales Pitch (45/100)

At 8:42

Selling a tool as a way to bypass the actual work 🛠️

Why this score: He's presenting a specific AI tool as a magic solution to generate content, rather than a research aid. It's a pitch disguised as advice.

Original quote: “you could use something like thesis AI, which you can put all of this literature into thesis AI and get a literature review.”

AI generates the bulk, human 'brain' just filters it 🧠 — Loaded Language (45/100)

At 10:30

Calling it 'magic excellent academic brain' is just fluff to make a shortcut sound like high-level thinking 🎭

Why this score: Uses flowery, self-serving language to mask the fact that they're describing a process of heavy curation rather than original research.

Original quote: “really doing is generating all of these literature reviews and then using your magic excellent academic brain to work out what you do like and what you don't like”

Using LLMs to check if work meets specific criteria — Confidence Mismatch (45/100)

At 13:20

Promoting a chatbot as a compliance officer for academic rigor 🤖

Why this score: He's acting like a prompt to an LLM is a substitute for actual academic judgment. It's just checking boxes, not critical thinking.

Original quote: “you can just say, hey, this is the matrix that I need to sort of satisfy or the uh learning outcomes for my literature review.”

Claiming AI tools provide automated summary and critique — Plain Sales Pitch (45/100)

At 13:47

Selling the 'convenience' of automated critique without showing real depth 📈

Why this score: He is demonstrating the features of a tool as if they are universal benefits, ignoring how shallow an AI's 'assessment' actually is.

Original quote: “You can actually sort of like put in something this is a paper and it will give you an idea of the summary. to what works well, what can be improved, over assessment”

Suggesting users can ignore AI feedback to maintain control — Volume Game (45/100)

At 14:04

Selling the tool by immediately telling you how to ignore it 💀

Original quote: “And you don't have to agree with this AI reviewer. You can be like, "No, actually, I quite like the way I've talked about that and I have done what you've said."”

Promoting AI tools like 'paper wizard' as a way to validate research quality — Plain Sales Pitch (45/100)

At 14:32

Selling the 'safety net' of AI tools without explaining how they actually judge quality 🎭

Why this score: He's pitching these tools as a way to 'not fail,' but he never explains the logic an AI uses to determine if evidence is actually 'appropriate' or just a hallucination.

Original quote: “I absolutely love the fact that that can be done. And another one that can also do it is paper wizard. But ultimately, this AI review allows you to take a step back and be like, am I actually satisfying the appropriate kind of part of this literature review?”

Claiming feedback is 'soul destroying' and one of the most painful parts — Loaded Language (45/100)

At 15:41

Using 'soul destroying' to describe the standard academic feedback loop 💀

Why this score: He is using high-intensity emotional descriptors for a routine part of research to build empathy through shared suffering.

Original quote: “And that is one of the most painful parts of writing a literature review or any sort of part of academic writing is that you have to get feedback and it is soul destroying sometimes but that is part of the process.”

Recommending reading backwards to catch errors — a niche tactic — No Frame (75/100)

At 16:52

Just a practical tip for proofreading. No tricks here, just actual workflow advice 🛠️

Why this score: The speaker is offering a specific, actionable technique for catching typos by breaking the narrative flow. It's not a grand claim, just a useful method.

Original quote: “So start at the end, read the last paragraph, the second last paragraph because sometimes it's hard to see those silly little mistakes when you're so focused on the narrative.”

Calling this the 'ultimate workflow' — high-confidence labeling — Confidence Mismatch (45/100)

At 17:53

Calling a single set of tips the 'ultimate workflow' is a massive stretch 🚩

Why this score: There is no data provided to suggest this specific workflow is superior to all other academic methods. It's a subjective label used to close the segment with authority.

Original quote: “But be proud of what you created. This is the ultimate workflow for creating an awesome literature review”

Directing viewers to another video about AI detectors — a soft pitch — Plain Sales Pitch (45/100)

At 18:12

Using the end of a lesson to funnel viewers into more of his content 🔄

Why this score: While it's helpful context, it functions as a way to keep the viewer in his ecosystem by promising a solution to the 'AI problem' in another video.

Original quote: “go check out this video where I talk about using uh AI detectors and how you can get around them”