News for hackers. Stuff that matters.

RomulusHill

Re:Show HN: Don't Hit Send – the model answers while you type on Sunday September 13, 2026 @12:37AM (#49680066)
Well it's got editable response wait, so that it can re-think its response before sending it to you if the course of your message changes.

I just thought it was a nice idea to pre-generate the response (yes admittedly it burns more tokens) but with open models and frontier level capabilities trickling down to low cost models, I'm not enormously concerned about the cost aspect.

I think it would be quite nice to add microphone input at some point, so that I could see if it rivals nice human response times.

The "not the thing I want you to respond to" part, I understand what you mean, but with some tinkering you could get it to match your usual typing/speech behaviours and cadence so that it doesn't start talking about the wrong thing before you finish your message.

It's entirely open source https://github.com/scalattice/dont-hit-send

Show HN: Don't Hit Send – the model answers while you type

https://github.com/scalattice/dont-hit-send

Type. The model is already answering. There is no send button.Left pane is one long draft. Right pane is a stack of replies. Pause for ~350ms and it fires a normal streaming chat completion with the whole draft. Type again and it aborts the last request if that reply never produced text; if it did, that bubble stays and a new one stacks. Bubbles never rewrite. Enter is a newline.That is...

( Read More... | 3 comments | 3 points | on HN )
Re:Ornith-1.5: From Self-Scaffolding to Self-Improvement on Monday August 31, 2026 @07:40AM (#49508475)
Hi Gertlabs, my inference company has actually started offering Ornith1.5 today for 9B and 35B A3B.

If you are still interested, send me a message on X and I'll help you get started! https://x.com/romulushill

https://scalattice.com/models/ornith-1.5-9b/ https://scalattice.com/models/ornith-1.5-35b-a3b/

https://scalattice.com/developers/

Show HN: Scalattice Modelmeter. OSS price and latency bench for open models

https://scalattice.com/blog/modelmeter/

I recently released an inference API company (scalattice.com), but the process building it required a huge amount of benchmarking, so we built some internal tools that we felt gave accurate and reliable standards to work off.Today we've decided to release some of our internal tooling like our benchmark software (locally hosted, open source) you can connect any inference API to the software...

( Read More... | no comments | on HN )

Show HN: I built a hypervisor and client for inference on consumer compute

https://scalattice.com/blog/openai-sdk-scalattice/

I'm the founder of Scalattice, this is my second company, third total product. I'm a 2x founder building some challenging software, some easy software, and some curiosity based tools that I've just always wanted to be a part of!So here is Scalattice.Scalattice is an OpenAI-compatible inference API. You keep the OpenAI SDK, swap base_url + API key, and call open models (Qwen3, Llama...

( Read More... | no comments | on HN )