PromptDriven builds PDD: The Last Programming Language™. Prompts are source. Code is disposable. Regenerate, don't patch.

Palo Alto, CA
Joined July 2025
Prompt Driven retweeted
"People aren't ready, this is gonna change everything" You know what people weren't ready for? Fucking mammoths. Tigers eating them. Monkeys ripping their arms off. The black plague. The ice age. Smallpox. Vikings pulling up on the beach. Drinking water that gives you diarrhea until you die. Getting a scratch and losing your whole leg. The Mongols. The Spanish Inquisition. One volcano can send us back to the dark ages and these safety guys are gonna be shocked. Oh the robots didn't kill us? It was a volcano? Imagine their disappointment as the hot ash rains down on them. A solar flare is gonna explode your phone in your pocket your legs are gonna be covered in battery acid and your bank account will stop working. You're afraid of a computer program doing math? "Things are moving too fast" homie you live on a rock that periodically deletes everything. You are one the most luckiest entities in a 100 light year radius living during a golden era. Cheer up. My ancestors crossed an ocean in a wooden box because they ran out of fucking potatoes. "The social disruption will be enormous!" Nigga World War 2? World War 2? Hop in the people carrier we're landing on the beach. Are these people out of their fucking minds? Do they not know what we've survived already? A couple decades of air conditioning and people suddenly think oh this is the natural condition of mankind. No. We used to have eight kids because seven didn't make it. You're gonna be fine. Man the fuck up. Accelerate.
950
3,050
573
21,380
949,700
Benchmarking discipline is why PDD ships what it ships. @GregTanaka ran 40 coding tasks across BF16, MTP, and 8-bit on an M4 Max — and published the harness, hashes, and the parts that didn't replicate cleanly.
I ran Qwen3.8 27B three ways on a 128GB M4 Max. 8-bit decoded ~1.7× faster than BF16. It was also 12.5% SLOWER at 16K context. Same coding score. Same 3 failures. Here's what tok/s doesn't tell you 🧵
45
Prompt Driven retweeted
Performance of Qwen3.8-27B:
115
293
327
3,340
1,603,320
Prompt Driven retweeted
excited to be releasing open weights for muse glimmer today, a 30b model that runs on a single consumer gpu, with open weights for a version of muse spark 1.2 coming soon. two very different models, both headed into people's hands, with more to come.
Today we're also opening the weights for Muse Glimmer, a great 30B parameter dense model that can run locally. Soon we'll also release the weights for Muse Spark 1.2, our latest foundation model. Meta is a strong supporter of open source and I'm proud of these releases. Congrats to @alexandr_wang and the MSL team for all your great work on these models.
144
216
65
3,734
363,392
Prompt Driven retweeted
The AI productivity paradox, solved: LLMs are best at generating software that already exists which is exactly the sw nobody pays for Infinite supply → price of zero The only sw that makes money now is the sw AI can't generate & that's precisely the sw that's hardest to build
🤖 Made with AI
1
5
141
Prompt Driven retweeted
Ship a real product in a day. That is the whole brief. 🚀 Build Fast. Launch Loud, a one-day @Prompt_Driven development hackathon in Palo Alto on July 25. Direct AI agents through prompts, deploy, and demo to investors. 🔗RSVP: promptdriven.ai/events/build…. Building an AI product? @RocketRideAI Cloud is live. Sign up at rocketride.ai/ #Hackathon #AIAgents #RocketRideAI #RocketRideCloud #BayArea
1
3
54
Prompt Driven retweeted
TokenRouter is sponsoring Build Fast Launch Loud, the @Prompt_Driven hackathon this Saturday July 25th in Palo Alto. We're backing you with developer credits for the day. You'll have access to all 100+ models on TokenRouter, including frontier open models like Kimi K3 and GLM 5.2. 12 hours to build and ship a live AI product using Prompt Driven Development, then demo what you built to investors from @M13Company , @500GlobalVC, and @blitzscaling Ventures. Registration is free and open: promptdriven.ai/events/build…
4
3
24
3,292
We just shipped the first programmatic-video use case for Prompt Driven at film scale. UNWRITTEN: a 3-minute AI short film by @sisozo_ & @GregTanaka just made Top 5 Best Film at @soulscapefilm 2026 (out of 39 films). Here's how we built it in 36 hours 🧵
7
1
476
Every shot was rendered on @TapNow: @sisozo_'s script drove the node-based workflow directly: same hero ref, same directive across all 18 shots. Programmable AI cinema. AI Tool: TapNow cc @tapnow_ai #TapTV #tapnow #Soulscape #TapTVArena
1
86
The biggest unlock in AI engineering is realizing your codebase is not an asset. It is a disposable artifact. Code is ephemeral. Your plain text prompts and strict tests are the only source of truth now. Stop being precious about text files. Delete them and regenerate.
1
58
Prompt Driven retweeted
Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI
989
5,619
2,415
38,322
19,455,818
The craziest part of building OpenClaw is watching an agent fail and realizing the bug is not in the Python. It is in my English. When you finally accept that plain text is your only real source code, debugging changes entirely. Delete the file, fix the spec, regenerate.
1
1
57
Stop treating your codebase like an asset. It is a liability. The required mental shift in AI coding is treating code as entirely ephemeral. Your raw prompts and strict tests are the only true source of truth. Everything else is just a disposable artifact.
33
Manually patching a bug in AI generated code is just manual labor in disguise. Stop playing tug of war with Cursor over broken logic. The code is entirely disposable. If it fails, delete the file, rewrite your prompt, and regenerate it from scratch.
38
The hardest mental shift in AI engineering is accepting that code is ephemeral. Your strict tests and raw prompts are the only real source of truth. The code itself is just a disposable artifact. Stop treating text files like sacred assets. If it breaks, delete it.
27
Was debugging a weird memory leak in OpenClaw today. I caught myself opening the Python file to manually patch it. Stopped, deleted the file, added a strict constraint to the prompt, and let the agent rebuild it. We really have to unlearn the habit of hoarding code.
1
36
That debt spike happens because we treat AI output like handwritten code we must maintain. The unlock is encoding your architecture into strict tests first. When tests act as hard boundaries, the code itself becomes a safely replaceable byproduct
19