Hacker News Reader

Comment by somewhatjustin | Hacker News Reader

> Claude Sonnet 5.5 and Claude Haiku 5.5 will follow in the coming weeks, with many of the same improvements to performance, efficiency, and safety.

Nice. I was starting to think that Haiku got abandoned.

View on HN

Found this announcement interesting since allegedly OpenAI is retiring their Terra tier. I think for everyday work, two models with various thinking efforts seem enough, plus some frontier level model like Fable or Astra to coordinate.

I personally use up to 3 models. Fable/Opus for planning, Opus/Sonnet for implementation depending on complexity.

I would maybe use Haiku 5.5 for highly parallel workflows like checking in on MRs or scanning my entire codebase.

Only reason I used Haiku was when I made Opus 5 run Haiku agents just to rewrite Opus 5's garbage output into something legible

Terra lost to Sol and Luna at every cost/performance point, it had no reason to exist.

At introduction, Terra was a good mid-tier model. Terra [high] was on the pareto frontier of DeepSWE's score over cost, if only ever so slightly.

When I had Sol orchestrate Luna and Terra as implementation agents, Sol was a lot happier with what Terra produced and would find far fewer issues than what was implemented by Luna.

But a few weeks after introduction, OpenAI slashed Luna's cost by 80% and Terra's only by 20%. Only then did it become uneconomical to run Terra and its reason to exist stopped.

Retiring the Terra tier? Their space-inspired lineup has only been out for 2 months, they're already messing with it?

Well you see Terra is being left behind.

I hope Haiku is Pareto better than Luna/Deepseek, so slashing its price by about 90%.

Claude code still uses it internally.

I'd be really curious to see benchmarks of haiku vs lower effort on bigger models. My own evals found Fable 5.1 at low to be better than Opus 5 on high.

Reply on news.ycombinator.com