41–50 of 179 posts
We tried GPT-5 for a RAG use case, and found that it performs worse than 4.1. We reverted and didn't look back.
We tried GPT-5 for a RAG use case, and found that it performs worse than 4.1. We reverted and didn't look back.
Can you elaborate on that? In which part of the RAG pipeline did GPT-4.1 perform better? I would expect GPT-5 to perform better on longer context tasks, especially when it comes to understanding the pre-filtered results and reasoning about them
To the authors of the site, please know that your current "Cookiebot by Usercentrics" is old and pretty much illegal. You shouldn't need to click 5 times to "Reject all" if accepting all is one click. Newer versions have a "Deny" button.
For development use cases, I switched to Sonnet 4.5 and haven't looked back. I mean, sure, sometimes I also use GPT-5 (and mini) and Gemini 2.5 Pro (and Flash), and also Cerebras Code just switched to providing GLM 4.6 instead of the previous Qwen3 Coder so those as well, but in general the frontier models are pretty good for development and I wouldn't have much reason to use something like Sonnet 4 or 3.7 or whateve…
I have canceled my Claude Max subscription because Sonnet 4.5 is just too unreliable. For the rest of the month I'm using Opus 4.1 which is much better but seems to have much lower usage limits than before Sonnet 4.5 was released. When I hit 4.1 Opus limits I'm using Codex. I will probably go through with the Codex pro subscription.
Tangential to this: what are the most reliable benchmarks for LLM in coding these days?
To the authors of the site, please know that your current "Cookiebot by Usercentrics" is old and pretty much illegal. You shouldn't need to click 5 times to "Reject all" if accepting all is one click. Newer versions have a "Deny" button.
Weirdly this site also requested bluetooth access on my mac.
Earlier quoted context omitted.
Weirdly this site also requested bluetooth access on my mac.
That would be the browser fingerprinting in action. I often get a lot of requests to use widevine on ddg's browser on android (which informs one about it) for I suspect similar reasons.
But when things get more complex, I prefer GPT-5, talking with it often gives me fresh ideas and new perspectives.
Earlier quoted context omitted.
Can you elaborate on that? In which part of the RAG pipeline did GPT-4.1 perform better? I would expect GPT-5 to perform better on longer context tasks, especially when it comes to understanding the pre-filtered results and reasoning about them
For large context (up to 100K tokens in some cases). We found that GPT-5: a) has worse instruction following; doesn't follow the system prompt b) produces very long answers which resulted in a bad ux c) has 125K context window so extreme cases resulted in an error
Earlier quoted context omitted.
Can you elaborate on that? In which part of the RAG pipeline did GPT-4.1 perform better? I would expect GPT-5 to perform better on longer context tasks, especially when it comes to understanding the pre-filtered results and reasoning about them
For large context (up to 100K tokens in some cases). We found that GPT-5: a) has worse instruction following; doesn't follow the system prompt b) produces very long answers which resulted in a bad ux c) has 125K context window so extreme cases resulted in an error