AI Paper Continuation: Two Different Approaches, One Writing Workflow

The first comparison came from a literature review paragraph. The paragraph had already begun discussing representative approaches for reducing lasing thresholds, and several more studies were about to follow.

At this cursor, I wasn't looking for another overview of the field. I simply needed a sentence that could connect naturally to the remaining literature.

Flowing stayed within the local narrative of the paragraph and smoothly transitioned toward the following studies.

ChatGPT generated a broader summary covering cavity engineering, defect passivation, compositional optimization, and several other directions.

Taken by itself, I actually liked the sentence. The problem wasn't correctness. It simply arrived too early: the remaining studies hadn't been introduced yet, so summarizing the field at this point interrupted the rhythm of the literature review.

One thing that stood out to me was Flowing's Evidence Card. Nearly every retrieved paper revolved around the same local topic, making it much easier for the continuation to stay aligned with the current discussion instead of drifting toward a broader overview.

In the end, I kept Flowing's continuation almost unchanged, while moving ChatGPT's sentence to the end of the section, where it worked well as an overall summary.

The second comparison came from the mechanism discussion. The previous paragraph had already introduced the energy-level diagram. The next sentence wasn't supposed to repeat that Ce³⁺ reduces the lasing threshold—it was supposed to explain why.

Flowing continued from intermediate energy states to carrier relaxation and eventually population inversion, extending the mechanistic reasoning step by step.

ChatGPT focused more on reinforcing conclusions that had already appeared, such as reduced non-radiative loss, improved carrier accumulation, and lower thresholds.

Both continuations were perfectly reasonable. The difference was simply their emphasis: one developed the mechanism further, the other reinforced what had already been established.

The third comparison was still inside the Introduction. Although the paragraph was introducing MHP micro/nano lasers, its real purpose wasn't to keep describing their advantages—it was preparing readers for the next question: why is reducing the lasing threshold still such an important challenge?

Instead of continuing to list material advantages, Flowing gradually narrowed the discussion toward the remaining tension between low-threshold operation and long-term stability. That final sentence almost wrote the transition into the next paragraph for me.

ChatGPT produced an excellent introduction to MHP micro/nano lasers. If the goal had simply been to introduce the field, I might even have preferred it. But at this point in the manuscript, I wanted the paragraph to guide readers toward the research question rather than continue the background.

Looking back, I suspect this was also influenced by how the two systems used context. Flowing combines the current paragraph with evidence retrieved from related papers. Most of the retrieved references here revolved around threshold reduction and stability, so the continuation naturally converged toward the upcoming discussion instead of remaining a general introduction.

The last comparison changed my perspective the most. This paragraph had already confirmed laser oscillation.

ChatGPT continued by discussing threshold behavior, linewidth narrowing, cavity Q factor, optical feedback, and light confinement. Everything was consistent with the local paragraph.

Flowing went one step further. It explicitly connected the discussion back to the Fabry–Pérot cavity that had already been established earlier in my manuscript, and linked it with the threshold analysis and cavity Q factor discussed in the following figures.

My first reaction was that this seemed slightly bold—the current paragraph never mentioned the Fabry–Pérot cavity. Then I remembered that I had already established it several pages earlier while discussing Figure 3c.

Flowing wasn't inventing a new conclusion. It was reusing information that already existed in my manuscript because it dynamically included the surrounding manuscript context during continuation. For a web-based ChatGPT workflow, manually copying Figure 3c, its caption, and the surrounding discussion into every prompt simply isn't something I would realistically do.

That was the moment I realized something: for scientific continuation, the most valuable context isn't always another fifty reference papers. Very often, it's simply the manuscript you've already written.