Before the free daily quota ends and the previous model is turned on.
You’re stacking two problems here: Using the free models, and using two different models in the same conversation (which will confuse the new model since it’s continuing a conversation it didn’t write).
Pay for one of the $20/month plans and use the top models and you’ll see much better results. I keep conversations with Opus 4.8 going through multiple compactions with no noticeable problems, and it’s very good at catching bugs[1].
Every LLM creates nonsense or the literal opposite of the correct meaning when translating into or from slavic languages (especially between them), while Google translate makes a spotless perfection even capturing the motive and the sentiment.
I actually mentioned this on a recent coding-agent-allowed interview, that the bugs they slipped into the starting code aren’t a good signal anymore since Claude caught all of them when prompted to “review this code before we get started”. Some of the bugs were pretty subtle too—the code worked and did something close to what it was supposed to do, and would only be obvious to a domain expert.
0) my post was observation about personal experience with free tools, not about state of the art. They do not match. Maybe some of my speech patterns were more alligned with old architectures, keeping them sane, but drive new models crazy. Maybe new models are just worse trained in tasks i work with. Maybe i am just incredibly unlucky this year having to dismiss 60% of chats as hallucinating.
I find the state of the free ai more important, since the majority of humanity will never buy any model, so free models will have more impact on society (in an optimistic universe where top model does not wipe the planet). Sorry for miscommunication, if the comparison free-to-free was not clear in the original.
Answering your points:
1) I said “before the previous model is turned on”. It starts hallucinating before the moment of switch, so it is incorrect statement that i mixed two models in one chat. I have specifically said the phrase because I expected that switching LLMs could in the mind of a reader be an assumption.
2) I do not intend to buy any subscription. I am comparing current free state of the technology with the previous free state of the technology. I have no doubt there are paid versions who can be orders of magnitude better.
Talking about translation I meant “every free LLM mentioned: claude sonnet 4.6, chatgpt 5.5, gemini 3.5 flash”. Google translate might be a specialised llm since it is performing a lot better, than the free general tools perform on my tasks.
“Makes something close to what is expected”—I mostly engage with strict domains (physics simulations or graph theory), so any formula/algorithm is either recalled correctly from the literature and is truth or is just incorrect (and then i have to scroll through literature to find manually). There is no blurry logic there. I do not engage with tasks like making ui.
You’re stacking two problems here: Using the free models, and using two different models in the same conversation (which will confuse the new model since it’s continuing a conversation it didn’t write).
Pay for one of the $20/month plans and use the top models and you’ll see much better results. I keep conversations with Opus 4.8 going through multiple compactions with no noticeable problems, and it’s very good at catching bugs[1].
Google Translate is an LLM.
I actually mentioned this on a recent coding-agent-allowed interview, that the bugs they slipped into the starting code aren’t a good signal anymore since Claude caught all of them when prompted to “review this code before we get started”. Some of the bugs were pretty subtle too—the code worked and did something close to what it was supposed to do, and would only be obvious to a domain expert.
0) my post was observation about personal experience with free tools, not about state of the art. They do not match. Maybe some of my speech patterns were more alligned with old architectures, keeping them sane, but drive new models crazy. Maybe new models are just worse trained in tasks i work with. Maybe i am just incredibly unlucky this year having to dismiss 60% of chats as hallucinating.
I find the state of the free ai more important, since the majority of humanity will never buy any model, so free models will have more impact on society (in an optimistic universe where top model does not wipe the planet). Sorry for miscommunication, if the comparison free-to-free was not clear in the original.
Answering your points:
1) I said “before the previous model is turned on”. It starts hallucinating before the moment of switch, so it is incorrect statement that i mixed two models in one chat. I have specifically said the phrase because I expected that switching LLMs could in the mind of a reader be an assumption.
2) I do not intend to buy any subscription. I am comparing current free state of the technology with the previous free state of the technology. I have no doubt there are paid versions who can be orders of magnitude better.
Talking about translation I meant “every free LLM mentioned: claude sonnet 4.6, chatgpt 5.5, gemini 3.5 flash”. Google translate might be a specialised llm since it is performing a lot better, than the free general tools perform on my tasks.
“Makes something close to what is expected”—I mostly engage with strict domains (physics simulations or graph theory), so any formula/algorithm is either recalled correctly from the literature and is truth or is just incorrect (and then i have to scroll through literature to find manually). There is no blurry logic there. I do not engage with tasks like making ui.