@petergostev Would you recommend it even for coding on a 20$ plus plan over Sol?
원본GPT-6.1-Terra 모델을 잠깐 써봤다. 실제로 써보는 게 꺼려지지 않는 임계점을 넘은 최초의 비프론티어 모델인 것 같다. 약간 더 단순해진 6.1-Sol 같은 느낌인데, 솔직히 꽤 좋다. 약간 겉도는 느낌이었던 기존 GPT-5.6-Terra랑은 전혀 다르다. 한도가 간당간당하거나, 장시간 실행되는 컴퓨터 작업이 필요하거나, 그냥 든든한 일꾼이 필요하다면 — 이걸로 충분할 거다. 인생을 바꿀 거라고까진 안 하겠지만,
0
0
0
0
댓글 27
-
-
@petergostev Is it any faster tok/s wise? Thinking of getting back to a plus plan to try it out
원본 -
@petergostev Thoughts about it as a daily driver for openclaw agents, unless its coding work etc??
원본 -
@petergostev gpt 6.1 sol very good for 20$ budget and also good usage tbh
원본 -
@petergostev felt like a simpler sol after a bit. what did it get wrong?
원본 -
@petergostev And it is really fast as well, just tried with video editing
원본 -
@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
원본 -
@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.
원본 -
@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.
원본 -
@petergostev Computer use? What for though?
원본 -
@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⚡️
원본 -
@petergostev Curious what you'd still hand to Sol instead
원본 -
@petergostev So basically tell 6.1 sol to plan and verify 6.1 terra as his worker?
원본 -
@petergostev For 20$ is it going to replace Deepseek-v4.1-flash for me? better quality?
원본 -
@petergostev That’s a meaningful shift if it feels good enough for everyday use without constantly needing the frontier model oneself
원본 -
@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
원본 -
@petergostev 6.1 terra feels like it was optimized to run dots for $20 / month users
원본 -
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?
원본 -
@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
원본 -
@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.
원본 -
@petergostev it's promising in terms of pricing, but it's very lazy https://x.com/atomic_chat_hq/status/2114811032816476638?s=20
원본 -
@petergostev Solid workhorse
원본 -
@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.
원본 -
@petergostev Opus 5.5
원본 -
@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.
원본 -
@petergostev 속도가 빠르고+작은단위로 시킨것만 잘 한다면 최고의 모델 아닐까요
원본 -
@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。
원본
스크롤하면 더 불러옵니다