model roundup

Haiku 4.5

6 items · started 2026-05-10 · closed 2026-05-16

  1. I just launched Socratize (socratize.io) - a rebranded and rebuilt version of FixAI, our original B2C experiment. This time it's B2B-only: teams use it to practice uncomfortable workplace conversations - difficult feedback, client escalati…

  2. I build context/harness optimization tooling, so provider-side serialization quirks actually matter to me. If you're optimizing over prompts, you need to know exactly what hits the model.

  3. I'm building an automated mail generation pipeline using Claude Haiku 4.5 OnPremise but the knowledge cutoff June 2025. This model needs to handle temporal expressions correctly like : next Monday end of the week this month 16 May 16 May 2…

  4. I'm on Claude Max 5x ($100/mo) and wanted to know if I'm overpaying. Every "should I switch" post here runs on vibes, so I parsed my actual usage from ~/.claude/projects/*.jsonl and applied Anthropic's per-MTok pricing.

  5. With the lowering usage limit in Claude, I am thinking of jumping ship to Chinese AI, since the benchmark is already very near compared to Sonnet or Haiku 4.5 , but for a fraction of the price. I am not worried about where is my data endin…

  6. With the lowering usage limit in Claude, I am thinking of jumping ship to Chinese AI, since the benchmark is already very near compared to Sonnet or Haiku 4.5 , but for a fraction of the price. I am not worried about where is my data endin…

← all threads