Many users rejected OpenAI GPT-5.6 Sol's 54% token efficiency claims for agentic coding because the model drains rate limits much faster than prior versions, while a few noted productivity improvements.
Based on 22 visible X reactions from 171 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@kimmonismus Bro, it's like you're just burning money. I really hate what these companies have turned into. Before, I could pay for a subscription and actually use it for a while. Now, after only one or two prompts, thelimit is already over. I miss when OpenAl used to give us 2x the tokens.
@kimmonismus It is the only model yet which gonna increase the productivity, also chatgpt app is a generational run
@kimmonismus Atleast it is much much more token efficient than opus and fable
GPT-5.6 Sol is 54% more token-efficient for agentic coding tasks, according to Sam Altman. GPT-5.6 Sol is great. But token efficiency is the one thing I just can't seem to confirm. I've never used up my rate limits faster than I do now - even on the "Pro" tier. https://x.com/kimmonismus/status/2075608495756333087/photo/1 https://twitter.com/kimmonismus/status/2075577730741981538
Seriously... pretty tough to work with 5.6. It burns through your rates like nothing before. https://x.com/kimmonismus/status/2075693686604619948/photo/1 https://twitter.com/kimmonismus/status/2075608495756333087
third time today: https://x.com/kimmonismus/status/2075695937624621342/photo/1
Many users rejected OpenAI GPT-5.6 Sol's 54% token efficiency claims for agentic coding because the model drains rate limits much faster than prior versions, while a few noted productivity improvements.
Based on 22 visible X reactions from 171 accounts; directional sample.
Ask a question below.
Published answers will appear here.
third time today: https://x.com/kimmonismus/status/2075695937624621342/photo/1