DEVOURED
PSA: Starting today, GPT 6.1 Sol has a default context window of 500k
GPT 6.1 Sol has increased its default context window to 500k, reducing the frequency of computational compactions for long-running tasks.
What: The model's context window has been upgraded from 272k to 500k tokens. This change applies to both Codex and ChatGPT Work, aiming to improve performance on long-context tasks by reducing the need for repeated memory compaction.
Why it matters: Increased context windows reduce the 'lossy' nature of long-running agentic tasks, making it easier to maintain state during complex, multi-step operations without needing frequent summarization.
Decoder
- Context window: The maximum number of tokens (words/characters) a model can consider at one time when generating a response.
Original article
PSA: starting today GPT 6.1 Sol has a default context window of 500k (from earlier 272k)
This should mean fewer (2-3x) compactions on long running tasks and faster E2E task completion!
All at no extra charge across Codex & ChatGPT Work - Enjoy!!
Explore all 54 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi