Claude Opus 4.6 and Sonnet 4.6

“Reading the tool calls Claude does while thinking shows a lot of trial and error”

“a bit more awe at these magic boxes (even the dumber ones like Opus and Sonnet)”

“Anything past that from those two have been bug-free”

“the degradation in speed and quality is too great above ~600k context”

“The present Sonnet/Opus versions (~4.8) will likely be what everyone in the enterprise might end up using eventually.”

“opus/sonnet had 0 problems with parens and types”

“That gets the machine (Opus and Sonnet at least) to go over the nearby code and occasionally mention something obvious.”

“sonnet/opus is better and what I use daily”

“Opus, Haiku and Sonnet are great models that i use all the time”

“I want to let it handle tricky stuff where other models can't address.”

“Context decay is real though — I've noticed quality dropping toward the end of long inputs even when the relevant text is there.”

“I felt like it was slower and generally worse than using 200K with context compaction”

“The 1M context is much easier to work with than compacting all the time”

“even with 200k context it starts to write gibberish”

“I'm very happy about this change. For long sessions with Claude it was always like a punch to the gut when a compaction came along.”

“it totally does not remain coherent past 200k”

“finally. before 1m, i must speak 60k context for just telling the past chat and project”

“1M is truly amazing. However, what is the incidence of hallucination?”

“the 1MM context degrades performance drastically”

“This is fantastic. I keep having to save to memory with instructions and then tell it to restore to get anywhere on long running tasks.”

“Compared to contexts of <200K, it degrades outputs rather than improves them”

“It seems to have been holding up pretty well until about 700k+.”

“When running long autonomous tasks it is quite frequent to fill the context, even several times.”

“context still rots at the same rate. 90k tokens consumed has just as bad results in 100k context window or 1M”

“I routinely generate applications for my personal use using OpenCode + Claude Sonnet/Opus.”

“there is no way Claude Code/Open Code with any modern model isn't able to generate a one hundred line script on the first try”

“Anthropic has nailed that Opus > Sonnet > Haiku.”

“It's much more consistent. Only 3 lines, numbered 4.6, 4.6, and 4.5”

“the latest Opus/Sonnet models are...ok. But there's still a lot left to be desired.”

“LLMs absolutely understand and write good Elixir”

“As long as I have access to GPT models or Sonnet/Opus, I never want to use Gemini.”

“I've done complex OTP and distributed work in tandem with Sonnet/Opus and they understand it well and happily keep up.”

“Sonnet/Opus behave like a mix of a diligent intern, or a peer. It does the work, doesn't talk too much”

“The local models hallucinate just enough that you end up spending more in lost time debugging than you would have paid for Sonnet or Opus”

“I've found sonnet and opus to be quite capable of generating json describing nodes and edges”

“I vastly prefer Claude over Codex”

“Models such as Sonnet or Opus 4.5 can generate thousands of lines of code per hour.”

“Very very rarely does the model fall off the rails.”

“faster, generally feels like a better coder, and make much prettier TUI/FEs”

“was able to make a fully working game”