Made a 90-second AI music video where every shot is a different decade's film stock. The prompt was longer than the script.
Into LLMs?
Get the best LLMs creations in your feed
Follow LLMs and the makers behind it. Join to spark, save, and remix any of these — the feed is yours to tune.
Top in LLMs
Thread: how I wired streaming tool-use with the Claude API in ~40 lines. The trick is buffering partial JSON until the block closes.
typescript
for await (const ev of stream) {
if (ev.type === 'content_block_delta')
buf += ev.delta.partial_json ?? '';
if (ev.type === 'content_block_stop')
handleTool(JSON.parse(buf)), buf = '';
}My Prompt as Art entry — a 14-line sonnet that doubles as a working SDXL prompt. Every line constrains the image. The craft IS the constraint. 🪶
A prompt is the only kind of writing where being weirdly specific is always rewarded. 'cinematic' does nothing. 'shot on expired Portra 400 at dusk' does everything.
DuckDB + an LLM = ask your CSV questions in English and get a chart back. Here's the 30-line bridge.
javascript
const sql = await llm.toSQL(question, schema);
const rows = await duck.query(sql);
render(autoChart(rows));
Prompt as Art: I made a prompt you read aloud and it makes no sense until you see the image it generates. Performance art for LLMs.
Shipped the hardest thing Ive built all year: a real-time inference router that load-balances across 3 GPU pools, falls back to CPU when they saturate, and streams tokens with sub-40ms first-token latency. Spent two weeks just on the backpressure logic so a slow client cant…
Latest
Prompt as Art: I made a prompt you read aloud and it makes no sense until you see the image it generates. Performance art for LLMs.
My Prompt as Art entry — a 14-line sonnet that doubles as a working SDXL prompt. Every line constrains the image. The craft IS the constraint. 🪶
Shipped the hardest thing Ive built all year: a real-time inference router that load-balances across 3 GPU pools, falls back to CPU when they saturate, and streams tokens with sub-40ms first-token latency. Spent two weeks just on the backpressure logic so a slow client cant…
DuckDB + an LLM = ask your CSV questions in English and get a chart back. Here's the 30-line bridge.
javascript
const sql = await llm.toSQL(question, schema);
const rows = await duck.query(sql);
render(autoChart(rows));A prompt is the only kind of writing where being weirdly specific is always rewarded. 'cinematic' does nothing. 'shot on expired Portra 400 at dusk' does everything.
Made a 90-second AI music video where every shot is a different decade's film stock. The prompt was longer than the script.
Thread: how I wired streaming tool-use with the Claude API in ~40 lines. The trick is buffering partial JSON until the block closes.
typescript
for await (const ev of stream) {
if (ev.type === 'content_block_delta')
buf += ev.delta.partial_json ?? '';
if (ev.type === 'content_block_stop')
handleTool(JSON.parse(buf)), buf = '';
}