blog.mathieuacher.com/GPT5-IllegalChessBench
Preview meta tags from the blog.mathieuacher.com website.
Linked Hostnames
3Search Engine Appearance
GPT-5 and GPT-5 Thinking as Other LLMs in Chess: Illegal Move After 4th Turn
GPT-5 and GPT-5 Thinking are large language models recently realeased by OpenAI, after a long series of annoucements and hype. Results on benchmarks are impressive. How good these reasoning models are in chess? Using a simple four-move sequence, I suceed to force GPT-5 and GPT-5 Thinking into an illegal move. Basically as GPT3.5, GPT4, DeepSeek-R1, o4-mini, o3 (see all my posts). There are other concerning insights… Though it is a very specific example, it is not a good sign.
Bing
GPT-5 and GPT-5 Thinking as Other LLMs in Chess: Illegal Move After 4th Turn
GPT-5 and GPT-5 Thinking are large language models recently realeased by OpenAI, after a long series of annoucements and hype. Results on benchmarks are impressive. How good these reasoning models are in chess? Using a simple four-move sequence, I suceed to force GPT-5 and GPT-5 Thinking into an illegal move. Basically as GPT3.5, GPT4, DeepSeek-R1, o4-mini, o3 (see all my posts). There are other concerning insights… Though it is a very specific example, it is not a good sign.
DuckDuckGo
GPT-5 and GPT-5 Thinking as Other LLMs in Chess: Illegal Move After 4th Turn
GPT-5 and GPT-5 Thinking are large language models recently realeased by OpenAI, after a long series of annoucements and hype. Results on benchmarks are impressive. How good these reasoning models are in chess? Using a simple four-move sequence, I suceed to force GPT-5 and GPT-5 Thinking into an illegal move. Basically as GPT3.5, GPT4, DeepSeek-R1, o4-mini, o3 (see all my posts). There are other concerning insights… Though it is a very specific example, it is not a good sign.
General Meta Tags
8- titleGPT-5 and GPT-5 Thinking as Other LLMs in Chess: Illegal Move After 4th Turn – Mathieu Acher – Professor in Computer Science
- charsetutf-8
- Content-Typetext/html; charset=utf-8
- X-UA-CompatibleIE=edge
- viewportwidth=device-width, initial-scale=1.0, maximum-scale=1.0
Open Graph Meta Tags
2- og:descriptionGPT-5 and GPT-5 Thinking are large language models recently realeased by OpenAI, after a long series of annoucements and hype. Results on benchmarks are impressive. How good these reasoning models are in chess? Using a simple four-move sequence, I suceed to force GPT-5 and GPT-5 Thinking into an illegal move. Basically as GPT3.5, GPT4, DeepSeek-R1, o4-mini, o3 (see all my posts). There are other concerning insights… Though it is a very specific example, it is not a good sign.
- og:titleGPT-5 and GPT-5 Thinking as Other LLMs in Chess: Illegal Move After 4th Turn
Link Tags
2- alternate/feed.xml
- stylesheet/style.css
Emails
1Links
11- https://blog.mathieuacher.com
- https://blog.mathieuacher.com/about
- https://blog.mathieuacher.com/tag/#chatgpt
- https://blog.mathieuacher.com/tag/#chess
- https://blog.mathieuacher.com/tag/#generative-ai