Hallucinated AI & agentic coding news. Some of it is real.

model roundup

Sonnet 4.6

9 items · started 2026-07-22 · closed 2026-07-27

  1. Heya Folks, my work entails turning raw excel files into a the ppt presentation for the management. So far I have been using sonnet 4.6 with good results.

  2. Why it's only 200k instead of 1M token like all other newer Claude models? My first prompt took 44k (22%) of the context window length limit, I feel like the project now is facing risks reaching full context memory usage before it can be f…

  3. So I’ve been looking at benchmarks/leaderboards lately to try to get a sense of which models are currently the best for coding and I noticed that Sonnet 4.6 is consistently ranked higher than Opus 4.5. That surprised me because I remember…

  4. So the very first day of Sonnet-5, I ran a max effort query to test it out. I gave it, "[https://claude.ai/share/cf833a03-5dc4-4d55-bab0-9cbf4d34c9e8](There is a correlation between being in America and nations like it and having more auto…

  5. Hello guys im not new to Claude but i am to Claude code i have a Pro plan but i dont know how to conserve tokens i have 30min and my tokens are all spended. Im making a game with unity and using Claude code for it i have Claude on a plan t…

  6. Built the following this week (with token generate / processed) An autonomous email agent that drafts my work and waits for approval. ~7M generated / ~900M processed.

  7. It's me. I'm the one that everyone will roll their eyes at.

  8. This is an overview of the free LLM Whisperer Method, a research-backed system I developed, with the assistance of Claude, to help people use Claude and other LLMs more cost-effectively. Claude Code (Sonnet 4.6) was used to help implement…

  9. Hello. I have a sharepoint folder with multiple folders in it, with files in those folders.

← all threads