cd /news/ai-products/show-hn-don-t-hit-send-the-model-ans… · home topics ai-products article
[ARTICLE · art-127458] src=github.com ↗ pub= topic=ai-products verified=true sentiment=· neutral

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

Scalattice released Don't Hit Send, an open-source chat interface that fires a streaming chat completion roughly 350ms after the user pauses typing, with no send button. The tool aborts the prior request if the previous reply produced no text, keeps completed replies as stacked bubbles that never rewrite, and is distributed as stdlib Python under the MIT license with the API key staying on the user's machine. It defaults to Scalattice's OpenAI-compatible endpoint, and any host supporting /v1/chat/completions works via Settings or environment variables.

read1 min views6 publishedSep 12, 2026

Type. The model is already answering. There is no send button.

Left pane is one long draft. Right pane is a stack of replies. 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 overlapping unary streams, not a duplex socket. Same shape as ghost-text, pointed at a conversation instead of a code line. The bit that took the work is the hold: do not fire on "and N" while someone is still typing "and NASA".

git clone [https://github.com/scalattice/dont-hit-send.git](https://github.com/scalattice/dont-hit-send.git)
cd dont-hit-send
export SCALATTICE_API_KEY=slt_...   # or OPENAI_API_KEY + OPENAI_BASE_URL

./run.sh

Stdlib Python, MIT, key stays on your machine. Defaults to Scalattice OpenAI-compat; any host that speaks /v1/chat/completions works from Settings or env.

Browser demo on our inference platform (sign-in after a short try): https://scalattice.com/dont-hit-send/ Why've we built this? The conventional AI chat interface is overdone and lacks innovation, I've personally been building agentic software for a while now and feel a lack of innovation in the interactivity. This is a step towards trialling some different inference interfaces!

Comments URL: [https://news.ycombinator.com/item?id=49669012](https://news.ycombinator.com/item?id=49669012)

Points: 1

── more in #ai-products 4 stories · sorted by recency
── more on @scalattice 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-don-t-hit-se…] indexed:0 read:1min 2026-09-12 ·