home.social

#kagitranslate — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #kagitranslate, aggregated by home.social.

fetched live
  1. Kagi Blog: Kagi Translate is back. “Today, Kagi Translate is moving to a freemium model and launching a new standalone Individual subscription for $8/month. Anyone with a Kagi account can continue using Translate for free with a limited monthly allowance. For people who use it more regularly, the new Individual plan includes all Kagi Translate features. Translate will also continue to be […]

    https://rbfirehose.com/2026/09/14/kagi-blog-kagi-translate-is-back/
  2. Kagi Blog: Kagi Translate is back. “Today, Kagi Translate is moving to a freemium model and launching a new standalone Individual subscription for $8/month. Anyone with a Kagi account can continue using Translate for free with a limited monthly allowance. For people who use it more regularly, the new Individual plan includes all Kagi Translate features. Translate will also continue to be […]

    https://rbfirehose.com/2026/09/14/kagi-blog-kagi-translate-is-back/
  3. Kagi Blog: Kagi Translate is back. “Today, Kagi Translate is moving to a freemium model and launching a new standalone Individual subscription for $8/month. Anyone with a Kagi account can continue using Translate for free with a limited monthly allowance. For people who use it more regularly, the new Individual plan includes all Kagi Translate features. Translate will also continue to be […]

    https://rbfirehose.com/2026/09/14/kagi-blog-kagi-translate-is-back/
  4. Kagi Blog: Kagi Translate is back. “Today, Kagi Translate is moving to a freemium model and launching a new standalone Individual subscription for $8/month. Anyone with a Kagi account can continue using Translate for free with a limited monthly allowance. For people who use it more regularly, the new Individual plan includes all Kagi Translate features. Translate will also continue to be […]

    https://rbfirehose.com/2026/09/14/kagi-blog-kagi-translate-is-back/
  5. Kagi Blog: Kagi Translate is back. “Today, Kagi Translate is moving to a freemium model and launching a new standalone Individual subscription for $8/month. Anyone with a Kagi account can continue using Translate for free with a limited monthly allowance. For people who use it more regularly, the new Individual plan includes all Kagi Translate features. Translate will also continue to be […]

    https://rbfirehose.com/2026/09/14/kagi-blog-kagi-translate-is-back/
  6. N'empêche #kagitranslate hors ligne pour les utilisateurs gratuits c'est bien la preuve que ça leur coûtait trop cher.
    Je suis sûr que c'était un llm derrière optimisé pour la traduction (pas possible de donnée autant de contexte à chaque fois sinon).
    Pas étonnant que ça devait leur coûter la peau des fesses 😅 mais malgré tout il était particulièrement bon par rapport aux autres...

  7. N'empêche #kagitranslate hors ligne pour les utilisateurs gratuits c'est bien la preuve que ça leur coûtait trop cher.
    Je suis sûr que c'était un llm derrière optimisé pour la traduction (pas possible de donnée autant de contexte à chaque fois sinon).
    Pas étonnant que ça devait leur coûter la peau des fesses 😅 mais malgré tout il était particulièrement bon par rapport aux autres...

  8. Kagi Blog: An update on Kagi Translate. “Some of you might have noticed that Translate no longer works when you’re signed out, or that it shows as offline. This is because we have temporarily turned off free access while we work through the cost of running Translate. If you have an active subscription, Translate still works.”

    https://rbfirehose.com/2026/06/06/kagi-blog-an-update-on-kagi-translate/
  9. Kagi Blog: An update on Kagi Translate. “Some of you might have noticed that Translate no longer works when you’re signed out, or that it shows as offline. This is because we have temporarily turned off free access while we work through the cost of running Translate. If you have an active subscription, Translate still works.”

    https://rbfirehose.com/2026/06/06/kagi-blog-an-update-on-kagi-translate/
  10. Kagi Blog: An update on Kagi Translate. “Some of you might have noticed that Translate no longer works when you’re signed out, or that it shows as offline. This is because we have temporarily turned off free access while we work through the cost of running Translate. If you have an active subscription, Translate still works.”

    https://rbfirehose.com/2026/06/06/kagi-blog-an-update-on-kagi-translate/
  11. Kagi Blog: An update on Kagi Translate. “Some of you might have noticed that Translate no longer works when you’re signed out, or that it shows as offline. This is because we have temporarily turned off free access while we work through the cost of running Translate. If you have an active subscription, Translate still works.”

    https://rbfirehose.com/2026/06/06/kagi-blog-an-update-on-kagi-translate/
  12. Kagi Blog: An update on Kagi Translate. “Some of you might have noticed that Translate no longer works when you’re signed out, or that it shows as offline. This is because we have temporarily turned off free access while we work through the cost of running Translate. If you have an active subscription, Translate still works.”

    https://rbfirehose.com/2026/06/06/kagi-blog-an-update-on-kagi-translate/
  13. The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.

    This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.

    So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.

    I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.

    But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?

    Yes, Virginia, it can.

    P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.

    #LLM #AI #Kagi #KagiTranslate #Translation #Spanish #Python

  14. The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.

    This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.

    So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.

    I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.

    But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?

    Yes, Virginia, it can.

    P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.

    #LLM #AI #Kagi #KagiTranslate #Translation #Spanish #Python

  15. The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.

    This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.

    So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.

    I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.

    But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?

    Yes, Virginia, it can.

    P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.

    #LLM #AI #Kagi #KagiTranslate #Translation #Spanish #Python

  16. The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.

    This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.

    So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.

    I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.

    But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?

    Yes, Virginia, it can.

    P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.

    #LLM #AI #Kagi #KagiTranslate #Translation #Spanish #Python

  17. The context section of Kagi Translate is meant to provide additional context to help with getting a translation that fits the intended context. However, I suspected that meant it was actually a way of delivering instructions to the LLM, and I was not wrong.

    This started off very handy. KT will happily correct for typos in the input, or even outright mistakes, and produce the output it statistically infers that you want. So when I mistakenly used “pudé” (I did) instead of “pus” (I put) in a sentence, it incorrectly translated to “I put” in the output, because statistically that was more likely, the other wasn't grammatical in my sentence so wouldn't have appeared in any samples. Which is fine if you're translating to understand something, not so much if you want to see if you wrote the right thing.

    So I went into the context section and added, “Translate the meaning of what is written, not what you think the author meant.” And sure enough, it correctly translated my incorrect Spanish, errors and all.

    I’ve had less luck with persuading it not to hallucinate word definitions based on a typo’s similarity to a real word. In Mexico “abonar” is “to buy on credit" or “to buy in installments”. “Avonar” is not a word at all, but it sounds the same, and when I first heard the word, I wasn't sure which was correct. KT didn't help, because it made up a similar definition for “avonar”. So I thought it was correct when it wasn't. I've tried putting “Do not fix typos” in the context instructions, but I think it needs something more complex. Maybe asking it to run all the words through some other step.

    But then I began to wonder. What about the classic test of LLMs? Can it generate a Python program?

    Yes, Virginia, it can.

    P.S. Don't get me wrong, this is an incredibly useful translation program. Especially for understanding country-specific words and slang. And it does have a “proofread” feature which catches some (but not all) input errors. But GIGO still rules.

    #LLM #AI #Kagi #KagiTranslate #Translation #Spanish #Python

  18. you can make the kagi translator crash out if you turn it into an angry fedi user and try to force it to claim bluesky is the true decentralised platform

    it's scarily accurate at portraying a fedi user like this lmaoooo

    #Fediverse #Bluesky #Kagi #KagiTranslate

  19. you can make the kagi translator crash out if you turn it into an angry fedi user and try to force it to claim bluesky is the true decentralised platform

    it's scarily accurate at portraying a fedi user like this lmaoooo

    #Fediverse #Bluesky #Kagi #KagiTranslate

  20. you can make the kagi translator crash out if you turn it into an angry fedi user and try to force it to claim bluesky is the true decentralised platform

    it's scarily accurate at portraying a fedi user like this lmaoooo

    #Fediverse #Bluesky #Kagi #KagiTranslate

  21. you can make the kagi translator crash out if you turn it into an angry fedi user and try to force it to claim bluesky is the true decentralised platform

    it's scarily accurate at portraying a fedi user like this lmaoooo

    #Fediverse #Bluesky #Kagi #KagiTranslate

  22. you can make the kagi translator crash out if you turn it into an angry fedi user and try to force it to claim bluesky is the true decentralised platform

    it's scarily accurate at portraying a fedi user like this lmaoooo

    #Fediverse #Bluesky #Kagi #KagiTranslate

  23. Made the unfortunate discovery that the Kagi translator allows custom languages, and is an LLM under the hood (at least for the custom languages)

    #Kagi #KagiTranslate

  24. Made the unfortunate discovery that the Kagi translator allows custom languages, and is an LLM under the hood (at least for the custom languages)

    #Kagi #KagiTranslate

  25. Made the unfortunate discovery that the Kagi translator allows custom languages, and is an LLM under the hood (at least for the custom languages)

    #Kagi #KagiTranslate

  26. Made the unfortunate discovery that the Kagi translator allows custom languages, and is an LLM under the hood (at least for the custom languages)

    #Kagi #KagiTranslate

  27. Made the unfortunate discovery that the Kagi translator allows custom languages, and is an LLM under the hood (at least for the custom languages)

    #Kagi #KagiTranslate

  28. 🚀🚀 Breaking news: Kagi Translate finally deciphers the enigmatic dialect of LinkedIn Speak, bringing the world one step closer to understanding corporate jargon! 🎩✨ Now you too can transform your plain English into a mystical blend of #buzzwords and hollow phrases, perfect for impressing your imaginary boardroom audience. 🙄👏
    translate.kagi.com/?from=en&to #KagiTranslate #LinkedInSpeak #CorporateJargon #BusinessCommunication #HackerNews #ngated

  29. 🚀🚀 Breaking news: Kagi Translate finally deciphers the enigmatic dialect of LinkedIn Speak, bringing the world one step closer to understanding corporate jargon! 🎩✨ Now you too can transform your plain English into a mystical blend of #buzzwords and hollow phrases, perfect for impressing your imaginary boardroom audience. 🙄👏
    translate.kagi.com/?from=en&to #KagiTranslate #LinkedInSpeak #CorporateJargon #BusinessCommunication #HackerNews #ngated

  30. 🚀🚀 Breaking news: Kagi Translate finally deciphers the enigmatic dialect of LinkedIn Speak, bringing the world one step closer to understanding corporate jargon! 🎩✨ Now you too can transform your plain English into a mystical blend of #buzzwords and hollow phrases, perfect for impressing your imaginary boardroom audience. 🙄👏
    translate.kagi.com/?from=en&to #KagiTranslate #LinkedInSpeak #CorporateJargon #BusinessCommunication #HackerNews #ngated

  31. 🚀🚀 Breaking news: Kagi Translate finally deciphers the enigmatic dialect of LinkedIn Speak, bringing the world one step closer to understanding corporate jargon! 🎩✨ Now you too can transform your plain English into a mystical blend of #buzzwords and hollow phrases, perfect for impressing your imaginary boardroom audience. 🙄👏
    translate.kagi.com/?from=en&to #KagiTranslate #LinkedInSpeak #CorporateJargon #BusinessCommunication #HackerNews #ngated

  32. 🚀🚀 Breaking news: Kagi Translate finally deciphers the enigmatic dialect of LinkedIn Speak, bringing the world one step closer to understanding corporate jargon! 🎩✨ Now you too can transform your plain English into a mystical blend of #buzzwords and hollow phrases, perfect for impressing your imaginary boardroom audience. 🙄👏
    translate.kagi.com/?from=en&to #KagiTranslate #LinkedInSpeak #CorporateJargon #BusinessCommunication #HackerNews #ngated