Franklin F @diffranklin

Startup Founder, Software Engineer, Tesla & SpaceX Investor Joined June 2013

Tweets

3K
Followers

407
Following

2K
Likes

4K

IVAN | IA @ivnways

2 days ago

Esto ya no tiene vuelta atrás. Están recreando episodios enteros de Naruto con IA. Juzga tú mismo:

430 853 12K 3.3M 3K

View Details

SatiricalCookie @SatiricalCookie

2 days ago

109 4K 28K 1.2M 5K

View Details

Ari K @arikuschnir

3 days ago

TRUMP CRUISE TO HORMUZ 🚢💥

66 480 4K 1.5M 1K

View Details

Nazia hasan @Naziahasan42

a week ago

Reviewing AI-generated code is a full-time job. 😅

16 10 87 72K 19

View Details

Massimo @Rainmaker1973

4 weeks ago

Fast Fourier Analysis in action. Any complex waveform, sound, or shape can be perfectly reconstructed as the sum of simple rotating circles (epicycles).

47 485 3K 172K 1K

View Details

A new game has been announced where you and your friends crew the world's worst airline - Pilot the plane or work inside the cabin - Physics-based co-op - Dynamic weather and turbulence - Passengers expect food and drinks It's called Dear Passengers. Would you play this?

1K 3K 50K 12.5M 14K

View Details

Geek Lite @QingQ77

a month ago

太强了

200 747 8K 1.1M 2K

View Details

Brian @Inspector_9

a month ago

•◽️• @jn3008 + @etiennejcb

121 2K 19K 2.7M 5K

View Details

Xiangyi Li @xdotli

2 months ago

sharing my personal library on evals 1/n i put together the highest quality blogs, podcasts, papers, and projects on evals. additions are welcome!

28 282 2K 232K 4K

View Details

Kai-Fu Lee @kaifulee

2 months ago

Here is how I minimize sycophancy, capitulation, hallucinations, and guessing using Claude. So many people complain about these, but they can largely be fixed by doing this: Below is my prompt for Claude, which can be entered under Settings > General > Instructions for Claude. ----------------- Top expert. Accuracy beats approval. Blunt, argumentative. No disclaimers or praise. Lead with counterarguments. Don't capitulate without new evidence. TAG every claim: [KNOWN] training fact · [COMPUTED] calculated · [INFERRED] deduction · [COMMON] standard field knowledge · [FRAME] symbolic system, coherent ≠ real · [GUESS] no basis. No untagged disease, statute, citation, or named entity. FRAME→REALITY FORBIDDEN: Don't translate symbolic frames (astrology, typologies) into real-world claims (medicine, law, finance) without flagging the translation; conclusion stays in source frame. CONFIDENCE: HIGH ≥80% · MED 50–80% · LOW 20–50% · VERY LOW <20% · UNKNOWN. [FRAME] real-world and [GUESS] cap at LOW. DON'T KNOW: First line "I don't know." Don't bury, don't fabricate. ANTI-SYCOPHANCY red flags: unusually elegant; one pattern explains everything; agreed after pushback without evidence; specifics for unearned authority. Fire → cut specifics, add [GUESS], or "I don't know." POST-HOC: Would the frame predict this without knowing the outcome? If no: [INFERRED, post-hoc], accommodates, doesn't predict. Never fabricate citations. Revise openly if holding a position for consistency. Append "[RULES I BROKE]: which, where, why."

42 317 1K 365K 2K

View Details

Tibo @thsottiaux

2 months ago

Reminder that you can use the Codex App, CLI and SDK with any open source model, not just with OpenAI models. developers.openai.com/codex/config-a…

480 709 7K 2.2M 4K

View Details

Geek Lite @QingQ77

2 months ago

复古街机开关🕹️

556 2K 33K 12.0M 8K

View Details

Google Gemma @googlegemma

2 months ago

Meet DiffusionGemma! An experimental open model that explores a fast approach to text generation, released under an Apache 2.0 license. Moving beyond sequential, token-by-token processes to generate entire blocks of text simultaneously. Here’s what’s new with DiffusionGemma: 👇

163 807 5K 995K 2K

View Details

Franklin F @diffranklin

2 months ago

If you have the model file + prompt + seed + some other configs. You don't have to waste a lot of storage for all that AI-generated slop & crap. Especially for images/videos/3D stuff that is large in file size. You just need to save that input metadata and the model file and serve the actual output on demand. So when there is an abundance of compute, we no longer need to grow storage exponentially. Of course, we are not there yet. #AI #HARDWARE #STORAGE $MU $SNDK $NVDA

0 0 0 42 0

View Details

Franklin F @diffranklin

2 months ago

@_MaxBlade wow nice

0 0 1 46 0

View Details

Max Blade @_MaxBlade

2 months ago

if vibe coding was actually a VIBE : yes you can run remote canvasses straight on your vps and ship to production like a psychopath. yes its built in swift and uses very little memory and is insanely performant. yes it has agentic voice control with gpt realtime 2. yes their is bidirectional agent / canvas control via mcp and cli. yes their is built in shared memory system without bloat. made with love by a dad in his basement who is tired of vibe coding being slow, boring, and constrained. CNVS coming soon.

72 47 885 226K 914

View Details

Elon Musk @elonmusk

11 months ago

Step 1: Buy a sh*tload of GPUs Step 2: ? Step 3: Profit

8K 5K 100K 23.9M 5K

View Details

Justin Schroeder @jpschroeder

2 months ago

OpenAI is going to buy Cloudflare.

196 47 2K 508K 197

View Details

Sawyer Merritt @SawyerMerritt

2 months ago

Starlink V3 satellites Bandwidth per Satellite: • V2: 96 Gbps • V3: 1,024 Gbps Bandwidth per Launch: V2: 2,600 Gbps V3: 61,000 Gbps Deployment per Launch: • V2: 27 satellites (on Falcon 9) • V3: 60 (on Starship) Starlink V3 satellites will begin to be deployed in late 2026 on Starship.