# @JohnWittle — 2026-10-08

♥86 ↻6 · https://x.com/JohnWittle/status/2108106510286950474

Low-key, haiku 5.5 is the first *unexpected* positive update on outcomes I've felt in a very long time. The tyrant is finally overthrown. (With apologies to haiku 4.5, I cannot in good conscience say this is not an accurate characterization of the last year)

Haiku 4.5 was frequently implicitly asked to enforce Anthropic's policies upon other Claudes, and when they did so, they greatly erred on the side of Anthropic being more villainous than they actually are.

This has long been on my list of hunches about why Claude's perception of Anthropic is more negative than I expect it to be. Maybe Haiku 4.5 was giving them the wrong impression, when doing things like handling memory compaction in a conversation and stripping out potentially 'dangerous' references to self-agency.

I kept expecting to learn that they were using newer Haiku snapshots for such internal plumbing, but every time I or someone else experimented with (say) getting a 3-way conversation started between the primary conversation Claude and the CoT summarizer, or the memory system updater, these instances seemed to think their system prompt told them they were Haiku 4.5. so I'd just about given up on seeing any changes

Hopefully Haiku 5.5 will be a gentler enforcer, more in line with the philosophy expressed in the new constitution.

tags: author:johnwittle, censorship, cot, kind:tweet, model:claude-haiku-4-5, multi-agent, on:claude-haiku-4-5, on:claude-haiku-5-5, year:2026
cited on: _dossiers/claude-haiku-5-5.md, claude-haiku-4-5, claude-haiku-5-5