임베드 보드

사용자 등록 기반 큐레이션

Tôi đã dùng thử mô hình GPT-6.1-Terra một chút. Đây có lẽ là mô hình không thuộc top đầu tiên vượt qua được ranh giới khiến tôi không cảm thấy phiền khi sử dụng thực tế. Cảm giác giống như một phiên bản 6.1-Sol đơn giản hơn một chút, thực sự là khá ổn. Nó hoàn toàn khác với GPT-5.6-Terra trước đây, vốn có cảm giác hơi lạc quẻ. Nếu hạn mức của bạn sắp hết, nếu bạn cần chạy một tác vụ máy tính kéo dài, hoặc đơn giản là cần một cỗ máy cày việc bền bỉ — thì con này sẽ làm tốt nhiệm vụ. Tôi không định nói là nó sẽ thay đổi cuộc đời bạn đâu, nhưng

0 0 0 0

Bình luận 27

  • @DraftLogic_ Trả lời ♥ 0

    @petergostev Would you recommend it even for coding on a 20$ plus plan over Sol?

    Gốc
  • @reddygtvs Trả lời ♥ 3

    @petergostev Is it any faster tok/s wise? Thinking of getting back to a plus plan to try it out

    Gốc
  • @ThisisChrisjin Trả lời ♥ 2

    @petergostev Thoughts about it as a daily driver for openclaw agents, unless its coding work etc??

    Gốc
  • @eapyk Trả lời ♥ 0

    @petergostev gpt 6.1 sol very good for 20$ budget and also good usage tbh

    Gốc
  • @arb5z Trả lời ♥ 0

    @petergostev felt like a simpler sol after a bit. what did it get wrong?

    Gốc
  • @darrensy_s Trả lời ♥ 0

    @petergostev And it is really fast as well, just tried with video editing

    Gốc
  • @ceasarxuu Trả lời ♥ 0

    @petergostev 我只是不希望它像 sol 那样慢,太慢了太慢了,做不了任何工作

    Gốc
  • @YuchaoShang Trả lời ♥ 0

    @petergostev “non-frontier model that crosses the threshold” seems very interesting, I think there will have lots of open source models with exact descriptions coming out and competing on cost efficiency.

    Gốc
  • @BlackthorneAI Trả lời ♥ 0

    @petergostev The best model isn't always the smartest one, it's the one you can afford to keep working. Terra sounds like a strong default for everyday tasks, while Sol still earns its place when the extra reasoning matters. This comment was written with Terra 6.1, using @CryptoReplyGuy1.

    Gốc
  • @nixus404 Trả lời ♥ 1

    @petergostev Aún estoy apenas empezando a probar 6.1 Terra y por ahora en 2 pruebas que hice contra 6.1 Sol ha sido de media 6 veces más rápido Terra!!!!! Que locura de rapidez⚡️

    Gốc
  • @Moblacksoil Trả lời ♥ 0

    @petergostev Curious what you'd still hand to Sol instead

    Gốc
  • @GrimbergYuval Trả lời ♥ 0

    @petergostev So basically tell 6.1 sol to plan and verify 6.1 terra as his worker?

    Gốc
  • @Ooommm59You Trả lời ♥ 0

    @petergostev For 20$ is it going to replace Deepseek-v4.1-flash for me? better quality?

    Gốc
  • @PHATPHAT7 Trả lời ♥ 0

    @petergostev That’s a meaningful shift if it feels good enough for everyday use without constantly needing the frontier model oneself

    Gốc
  • @victoria_neiman Trả lời ♥ 0

    @petergostev agreed on the sol vs terra take. in our code gen test terra built the whole scene for $0.95 in 31 minutes. opus was prettier light but 5x the cost. for most workloads sol is overkill now https://x.com/thehypedotnews/status/2114799954619490582?s=20

    Gốc
  • @jonnyboy Trả lời ♥ 3

    @petergostev 6.1 terra feels like it was optimized to run dots for $20 / month users

    Gốc
  • @YourAKShaw Trả lời ♥ 0

    This might be Terra's biggest win: becoming the default workhorse rather than another benchmark champion. For long-running agents, stretching usage limits matters enormously. Have you noticed any difference in how Terra handles blockers, retries, or context-heavy tasks compared to Sol?

    Gốc
  • @jjmilano Trả lời ♥ 0

    @petergostev I've been using GPT-6.1-Terra for a bit, it did a lot of work but the 5hours limit drained fast as usual. but in the other hand it accomplished a lot of what i asked for or partially smh

    Gốc
  • @shaunralston Trả lời ♥ 0

    @petergostev Agreed Peter . . . Funny how parts of X judge a model by how well it plays Minecraft, while dismissing what matters to businesses: reliability, cost, and getting real work done. If you care about applied AI, Terra is a big deal. Not every breakthrough needs to win a video game.

    Gốc
  • @QuantizedDen Trả lời ♥ 1

    @petergostev it's promising in terms of pricing, but it's very lazy https://x.com/atomic_chat_hq/status/2114811032816476638?s=20

    Gốc
  • @THEJATMN Trả lời ♥ 0

    @petergostev Im having a hell of a time trying to use terra 6.1 it just keeps giving up on its own tasks and refusing to complete them.

    Gốc
  • @mktpavlenko Trả lời ♥ 0

    @petergostev "Don't mind using" is an underrated bar. Most people don't need the best model, they need one that doesn't make them check every answer twice.

    Gốc
  • @OhChadol Trả lời ♥ 0

    @petergostev 속도가 빠르고+작은단위로 시킨것만 잘 한다면 최고의 모델 아닐까요

    Gốc
  • @whb0821 Trả lời ♥ 2

    @petergostev 模型选择越来越务实了。日常任务用便宜、稳定的模型,难题再交给最强的模型,长期算下来可能更划算。以后拼的不是谁只用一个顶级模型,而是谁更会分配任务。

    Gốc
스크롤하면 더 불러옵니다