@petergostev Would you recommend it even for coding on a 20$ plus plan over Sol?
मूलमैंने थोड़ी देर के लिए GPT-6.1-Terra मॉडल का इस्तेमाल किया। यह शायद पहला नॉन-फ्रंटियर मॉडल है जो उस सीमा को पार करता है जिसे इस्तेमाल करने में मुझे असल में कोई आपत्ति नहीं है। यह थोड़ा सा सरल 6.1-Sol जैसा महसूस होता है, जो ईमानदारी से कहें तो काफी अच्छा है। यह GPT-5.6-Terra जैसा बिल्कुल नहीं है, जो थोड़ा बेमेल सा लगता था। अगर आपकी लिमिट कम है, अगर आपको कोई लंबे समय तक चलने वाला कंप्यूटर टास्क चाहिए, या बस एक ठोस काम करने वाला मॉडल चाहिए — तो यह काम कर जाएगा। मैं यह नहीं कह रहा हूँ कि यह आपकी ज़िंदगी बदल देगा, लेकिन
0
0
0
0
टिप्पणियाँ 27
-
-
@petergostev Is it any faster tok/s wise? Thinking of getting back to a plus plan to try it out
मूल -
@petergostev Thoughts about it as a daily driver for openclaw agents, unless its coding work etc??
मूल -
@petergostev gpt 6.1 sol very good for 20$ budget and also good usage tbh
मूल -
@petergostev felt like a simpler sol after a bit. what did it get wrong?
मूल -
@petergostev And it is really fast as well, just tried with video editing
मूल -
@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
मूल -
@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.
मूल -
@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.
मूल -
@petergostev Computer use? What for though?
मूल -
@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⚡️
मूल -
@petergostev Curious what you'd still hand to Sol instead
मूल -
@petergostev So basically tell 6.1 sol to plan and verify 6.1 terra as his worker?
मूल -
@petergostev For 20$ is it going to replace Deepseek-v4.1-flash for me? better quality?
मूल -
@petergostev That’s a meaningful shift if it feels good enough for everyday use without constantly needing the frontier model oneself
मूल -
@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
मूल -
@petergostev 6.1 terra feels like it was optimized to run dots for $20 / month users
मूल -
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?
मूल -
@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
मूल -
@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.
मूल -
@petergostev it's promising in terms of pricing, but it's very lazy https://x.com/atomic_chat_hq/status/2114811032816476638?s=20
मूल -
@petergostev Solid workhorse
मूल -
@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.
मूल -
@petergostev Opus 5.5
मूल -
@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.
मूल -
@petergostev 속도가 빠르고+작은단위로 시킨것만 잘 한다면 최고의 모델 아닐까요
मूल -
@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。
मूल
스크롤하면 더 불러옵니다