Is The New Web Browsing in ChatGPT Any Good?

Is The New Web Browsing in ChatGPT Any Good?

by The AI Advantage

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 The AI Advantage 👥 480K 📅 September 30, 2023 ⏱ 10 min 👁 37K 📄 expert opinion 🧭 2026-09-08
Available in: English (current) Français

Keywords

ChatGPTBingbrowsingweb pilotOpenAI

Summary

The video reviews the re-enabling of Bing browsing in ChatGPT Plus, which occurred in late September 2023. The creator compares the new version with the one from May 2023, testing three use cases: creating an advertising campaign, researching YouTube creators, and preparing for a job interview. He finds that the new browsing feature often fails to trigger, requires multiple attempts, and produces generic results compared to the previous version. He also notes that websites can now restrict access via robots.txt, which may explain the reduced functionality. He compares it with the Web Pilot plugin, which he finds more reliable for accessing web content. He concludes that the browsing feature is not yet reliable and recommends copying and pasting relevant data directly into ChatGPT for controlled results. The video provides practical tips and acknowledges the limitations of the current implementation.

139 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides practical, hands-on value by testing the feature in real scenarios and comparing it with previous versions and alternatives. The argumentation is based on direct experience, but lacks systematic methodology and statistical evidence. The creator’s conclusions are reasonable and honest, acknowledging the limitations of the feature.

Scientific Rigor, Source Quality, Title Accuracy

The video does not cite scientific sources but references OpenAI’s announcement and the robots.txt mechanism. The title accurately reflects the content. The creator’s claims are based on personal testing, which is transparent but not rigorous. The video includes a promotional segment for his courses and resources, which is clearly separated from the content.

116 words

Title / Content Match

The title accurately reflects the content, which evaluates the new web browsing feature in ChatGPT.

Quality & Reliability

6/10

The video is a hands-on test of ChatGPT's browsing feature, based on the creator's direct experience. It lacks systematic methodology and external verification, but provides practical insights and honest limitations.

Key Moments

Markers derived by PSI from the transcript: the creator did not define chapters.

Cited Sources

Concurring Sources

  • OpenAI's announcement on browsing — Mentioned in the video as the official source for the feature's release.

Dissenting Sources

  • Web Pilot plugin — The creator finds Web Pilot more reliable than Bing browsing, contrary to the expectation that the new feature would be superior.

Contribution & Novelties

The video provides a practical, up-to-date assessment of ChatGPT’s browsing feature after its re-enablement, highlighting its limitations and comparing it with alternatives. It offers actionable advice for users.

Pour aller plus loin :

  • ChatGPT — Background on the AI model.
  • Robots.txt — Explanation of the protocol that governs bot access to websites.
  • Bing — Overview of Microsoft’s search engine used in the browsing feature.

64 words

Radar Profile

The radar profile shows moderate scores across all dimensions, indicating a balanced but not exceptional video. The content is informative but lacks depth and rigorous sourcing.

Reliability 5/10