Don't Hit Send
the model answers while you type
Details
- External ID
- 49669012
- Source
- HN
- Company
- —
- Product
- Don't Hit Send
- Website domain
- github.com
- Launched
- Sept. 12, 2026
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.4393939393939394
- Tags
- —
- Fetched at
- Sept. 16, 2026, 5:01 p.m.
- Updated at
- Sept. 16, 2026, 5:01 p.m.
Description
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 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 cd dont-hit-send export SCALATTICE_API_KEY=slt_... # or OPENAI_API_KEY + OPENAI_BASE_URL ./run.sh # http://127.0.0.1:8766Stdlib 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!
Enrichment
- Theme
- autonomous ai agents for business
- Vertical
- Horizontal
- Function
- Content generation
- Audience
- Prosumer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- ai written replies while you type
- Manually corrected
- False
Could you build this?
Yes This is a sleek front-end wrapper that sends debounced requests with abort controllers to standard streaming LLM chat completion APIs as the user types.
Discussion
1 comment analyzed.
Concerns raised: Interrupts before user finishes composing, Adds unnecessary cost, Wastes compute/energy, Worse human experience, Not worth saving one keypress
Competitors
Other products that read as similar to this one — 140 launches clear the similarity bar, closest 8 shown.
Attention rank: #74 of 141 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 316 days after the earliest competitor.
- AI Reply · ph · 2026-09-15 · 1 upvotes · similarity 0.47
- MorrowCache · ph · 2026-09-30 · 2 upvotes · similarity 0.43
- Smillee · ph · 2026-09-10 · 2 upvotes · similarity 0.41
- ChatShelf · ph · 2026-09-10 · 1 upvotes · similarity 0.41
- ReplyME: AI Dating Replies · ph · 2026-09-14 · 2 upvotes · similarity 0.41
- AI Reply Assistant · ph · 2026-09-30 · 2 upvotes · similarity 0.40
- Banana Keyboard · ph · 2026-09-18 · 60 upvotes · similarity 0.40
- Sidestream · hn · 2026-01-06 · 6 upvotes · similarity 0.40
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a content generation tool for Government yet.