Simone De Palma
@simodepth.bsky.social
👾Tech SEO Specialist| Data Science Enthusiast
🔔 Did you know #OpenAI may keep a cached index of webpages?
When a page is fresh or heavy on #JavaScript, #ChatGPT can generate answers from related cached pages.
I built a small app using your OpenAI API to check the external_web_access endpoint
Tests and context -> github.com/simodepth96/...
When a page is fresh or heavy on #JavaScript, #ChatGPT can generate answers from related cached pages.
I built a small app using your OpenAI API to check the external_web_access endpoint
Tests and context -> github.com/simodepth96/...
GitHub - simodepth96/ChatGPT-Index-Console
Contribute to simodepth96/ChatGPT-Index-Console development by creating an account on GitHub.
github.com
November 29, 2025 at 7:43 PM
🔔 Did you know #OpenAI may keep a cached index of webpages?
When a page is fresh or heavy on #JavaScript, #ChatGPT can generate answers from related cached pages.
I built a small app using your OpenAI API to check the external_web_access endpoint
Tests and context -> github.com/simodepth96/...
When a page is fresh or heavy on #JavaScript, #ChatGPT can generate answers from related cached pages.
I built a small app using your OpenAI API to check the external_web_access endpoint
Tests and context -> github.com/simodepth96/...
I'm not surprised at all.
If you're based in the EU and have a proper look into your server logs, this is what you get.
The idea per se is smart as LLMs may slice .md faster than .html but if it doesn't become a standard in the W3C then it lives in thin air
If you're based in the EU and have a proper look into your server logs, this is what you get.
The idea per se is smart as LLMs may slice .md faster than .html but if it doesn't become a standard in the W3C then it lives in thin air
Shocking... ;) -> Study: LLMs.txt Shows No Clear Effect On AI Citations, Based On 300k Domains
"Analysis of 300k domains found LLMs.txt adoption is low & has no measurable link to AI citation frequency. SE Ranking’s crawl found llms.txt on 10.1% of domains. i.e. 9 out of 10 sites didn't have it."
"Analysis of 300k domains found LLMs.txt adoption is low & has no measurable link to AI citation frequency. SE Ranking’s crawl found llms.txt on 10.1% of domains. i.e. 9 out of 10 sites didn't have it."
LLMs.txt Shows No Clear Effect On AI Citations, Based On 300k Domains
An analysis of 300k domains found LLMs.txt file adoption is low and has no measurable link to AI citation frequency.
www.searchenginejournal.com
November 22, 2025 at 9:38 AM
I'm not surprised at all.
If you're based in the EU and have a proper look into your server logs, this is what you get.
The idea per se is smart as LLMs may slice .md faster than .html but if it doesn't become a standard in the W3C then it lives in thin air
If you're based in the EU and have a proper look into your server logs, this is what you get.
The idea per se is smart as LLMs may slice .md faster than .html but if it doesn't become a standard in the W3C then it lives in thin air
Reposted by Simone De Palma
this goes right along with my theory that the AI obsession in *users* is often bc…
1. they were never educated (esp "ipad generation") & don't know how computers work
2. our tools and services are all SO AWFUL NOW, degraded at best, actively user-hostile at worst
1. they were never educated (esp "ipad generation") & don't know how computers work
2. our tools and services are all SO AWFUL NOW, degraded at best, actively user-hostile at worst
November 15, 2025 at 6:47 PM
this goes right along with my theory that the AI obsession in *users* is often bc…
1. they were never educated (esp "ipad generation") & don't know how computers work
2. our tools and services are all SO AWFUL NOW, degraded at best, actively user-hostile at worst
1. they were never educated (esp "ipad generation") & don't know how computers work
2. our tools and services are all SO AWFUL NOW, degraded at best, actively user-hostile at worst
Reposted by Simone De Palma
Head to Skyline to attend an insightful session on ‘Technical SEO nightmares on client-side React web apps’ by @simodepth.bsky.social
#BrightonSEO
#BrightonSEO
October 23, 2025 at 2:14 PM
Head to Skyline to attend an insightful session on ‘Technical SEO nightmares on client-side React web apps’ by @simodepth.bsky.social
#BrightonSEO
#BrightonSEO
A test on 7 URLs with missing meta descriptions showed:
- Google and ChatGPT favoured H1S and structured text
- Perplexity relied on cached metas.
LLMs and AI search engines tend to mimic Google, preferring structured, self-contained content during retrieval.
👉🏻 seodepths.com/seo-research...
- Google and ChatGPT favoured H1S and structured text
- Perplexity relied on cached metas.
LLMs and AI search engines tend to mimic Google, preferring structured, self-contained content during retrieval.
👉🏻 seodepths.com/seo-research...
How Google & LLMs Replace Missing Meta Descriptions
Discover how Google and LLMs replace missing meta descriptions—pulling from H1s, bullet points, or cached content, often mimicking each other.
seodepths.com
September 1, 2025 at 5:31 PM
A test on 7 URLs with missing meta descriptions showed:
- Google and ChatGPT favoured H1S and structured text
- Perplexity relied on cached metas.
LLMs and AI search engines tend to mimic Google, preferring structured, self-contained content during retrieval.
👉🏻 seodepths.com/seo-research...
- Google and ChatGPT favoured H1S and structured text
- Perplexity relied on cached metas.
LLMs and AI search engines tend to mimic Google, preferring structured, self-contained content during retrieval.
👉🏻 seodepths.com/seo-research...
Gemini API Grounding might be the reference point to start optimising for fan-out search queries from #AIMode
In the screenshot, the results of a few tweaks to the #Python from the cookbook repository ai.google.dev/gemini-api/d...
🧵
In the screenshot, the results of a few tweaks to the #Python from the cookbook repository ai.google.dev/gemini-api/d...
🧵
August 22, 2025 at 3:46 PM
Gemini API Grounding might be the reference point to start optimising for fan-out search queries from #AIMode
In the screenshot, the results of a few tweaks to the #Python from the cookbook repository ai.google.dev/gemini-api/d...
🧵
In the screenshot, the results of a few tweaks to the #Python from the cookbook repository ai.google.dev/gemini-api/d...
🧵