lukax
Joined 15 years ago
Karma
917
Submissions
153
Member since
Jan 11
Recent submissions
Comment · 8 days ago
And now they can train on everything this community does. And with new models this community won't be needed anymore.
Comment · 12 days ago
Their inference server/service (wrapper around this engine) could still be written in Rust, this is just the engine.
This is written in Rust: https://github.com/deepseek-ai/deepseek-recipe
This DeepSeek Recipe is also mentioned here: https://zhuanlan.zhihu.com/p/2095560295930508953
Comment · 1 month ago
Yes, through OpenRouter.
Comment · 1 month ago
OpenCode checks model name and registers the appropriate tools.
const usePatch = model.modelID.includes("gpt-") && !model.modelID.includes("oss") && !model.modelID.includes("gpt-4")
Pi uses its own tools, like Armin wrote in the linked article.
Comment · 1 month ago
What matters more is that you use the tools that the target model was fine-tuned on.
E.g. for editing files with Claude models you should use Edit(file_path, old_string, new_string, replace_all) but with GPT models you should use apply_patch_call(patch) (where patch is a custom patch string with custom grammar).
It appears newer models are better at narive harness tool calls and worse at custom tools that look similar to default tools.
https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/
Comment · 1 month ago
https://news.ycombinator.com/submitted?id=vertigoruntime
This looks like a new account from a PR agency focusing on AI labs.
Comment · 2 months ago
This is only a problem with OpenAI Chat Completions API. With OpenAI Responses API and Anthropic Messages API a tool output can be text, image or file.
Comment · 2 months ago
DeepSeek-V4-Flash
Input (Cache Miss)
Previous: $0.14
New - Off-Peak: $0.22 (approx. 1.57x)
New - Peak: $0.44 (approx. 3.14x)
Input (Cache Hit)
Previous: $0.0028
New - Off-Peak: $0.007 (2.5x)
New - Peak: $0.014 (5x)
Output
Previous: $0.28
New - Off-Peak: $0.66 (approx. 2.35x)
New - Peak: $1.32 (approx. 4.71x)
---
DeepSeek-V4-Pro
Input (Cache Miss)
Previous: $0.435
New - Off-Peak: $0.66 (approx. 1.51x)
New - Peak: $1.32 (approx. 3.03x)
Input (Cache Hit)
Previous: $0.003625
New - Off-Peak: $0.022 (approx. 6.07x)
New - Peak: $0.044 (approx. 12.14x)
Output
Previous: $0.87
New - Off-Peak: $1.98 (approx. 2.27x)
New - Peak: $3.96 (approx. 4.55x)
Comment · 3 months ago
Yes. They are.
Comment · 3 months ago
They somehow forgot to mention that Hugging Face tried to use frontier models to analyze the attack but all models rejected. They had to use GLM 5.2 deployed locally.
Comment · 3 months ago
Also for WASM? It's just not really there compared to Rust's wasm bindgen.
Comment · 3 months ago
I can highly recommend Rust for this. The same Rust engine powering web app (WASM + React), iOS (SwiftUI), Android (Kotlin Compose) and desktop (Tauri).
Comment · 3 months ago
Could it be that users of Pi are more senior and know better how to prompt and that's why the pass rate is higher?
Comment · 3 months ago
Yes, this is a known issue. A significant amount of Edit tool calls fails in Pi witg newer models.
https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/