product design & eng @perplexity_ai. prev design @eco, @quora, @guidebook co-founder. @northeastern alum. Will write css for coffee. work: https://xitter.cf/t.co/nK0sRsK84G
Orinda, CA
Joined July 2008
- Tweets5K
- Following1K
- Followers3K
- Likes9.8K
Pinned Tweet
Excited to share that I recently joined @perplexity_ai as a product designer / ui engineer, working alongside a phenomenal team (and @henrymodis, again!). AI-native search is just beginning to take flight and I’m happy to get to play a small part in its development. Let’s go!
Ground has been broken!
Recently i've been using @perplexity_ai computer to design an outdoor office for our property. It's insane how good it's gotten at visualizing the space, finding furniture that fits, exploring layouts, lighting, and even framing details (double checking w contractor!).
It even placed the office accurately in a generated 3d site plan from a video of me walking around the property and describing where it should go.
It's not perfect (yet), but being able to get this far on your own unlocks so much creativity. Really fun!
Pete Lada retweeted
You can now run Perplexity Computer fully local on your Mac with no cloud based inference, without WiFi too. Enjoy!
Pete Lada retweeted
REA (Reverse Engineer Anything) by @morluto is now a skill in Computer.
Ask Computer to reverse-engineer an app and it inspects how the app works without its source code, then builds a working version.
Tasks that use /reverse-engineer are free through October 31, up to 10,000 credits per user.
Here are 5 apps Computer made with it, available to try for a limited time:
1) Figma: Design with layers and auto-layout, plus sign-in, cross-device sync, and multiplayer editing. Try it: ui-editing.pplx.app
Recently i've been using @perplexity_ai computer to design an outdoor office for our property. It's insane how good it's gotten at visualizing the space, finding furniture that fits, exploring layouts, lighting, and even framing details (double checking w contractor!).
It even placed the office accurately in a generated 3d site plan from a video of me walking around the property and describing where it should go.
It's not perfect (yet), but being able to get this far on your own unlocks so much creativity. Really fun!
Pete Lada retweeted
Perplexity wins on Hugging Face Decision Index (benchmark for decision models). Our model is open-weights and accessible to all!
pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available.
It scores the highest on the new @huggingface Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs half as much as v1, at $0.02 per million input tokens.
huggingface.co/spaces/multim…
Pete Lada retweeted
We now give you the best model combinations for various efforts. Huge aura 🧊 from @magglevalentine and @cifilter 👏🏼
Try out Perplexity Computer - it’s very good!
It is wild to me how slept on @perplexity_ai is by the market. I use Perplexity Computer constantly.
Here is why:
1. I can share skills easily across my team easily in the cloud.
2. It is very good at model routing and selection and I have access to all the best models from all the model providers.
3. My perplexity computer tasks sync seamlessly between my desktop and cloud.
4. It is easy to build workflows from any task in computer for important reoccurring jobs.
5. Computer tasks process in the cloud so I don’t have to constantly have my desktop on and running.
Now they have solved a critical security concern for many AI users.
It isn’t perfect. I find that the design output for artifacts to be lower quality than using the same models in their own harnesses. Additionally it has bugs where tasks get hung up or take longer than they should to run.
Pete Lada retweeted
Set up a crypto DCA trading strategy using the Coinbase connector in Perplexity Computer
Pete Lada retweeted
In a compute and power-constrained world, a good chunk of agentic inference needs to move to local hardware. A drastic version of that is a fully local agent runtime, where the model (orchestrator and subagents) and the harness run locally. Portable Computer from Perplexity is this. Launching today for @nvidia DGX Spark.
Today we’re launching Portable Computer on @NVIDIA DGX Spark.
Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness all run on your local hardware. No cloud dependency.
Pete Lada retweeted
If your agent needs frontier web search, it's hard to beat Perplexity's Agent API (on any metric).
Introducing Web Search Benchmarks 🌐
Rankings of search tools across different models and configurations to help you decide how to ground your agent: openrouter.ai/benchmarks
Pete Lada retweeted
Holy moly, just stumbled upon some @perplexity_ai sketches from a lost time.
Designed by me, summer, & tully.
Sorry @henrymodis + @apostraphi I guess I never sent these?!
Pete Lada retweeted
We launched Projects today which has been a huge effort. Computer is now multiplayer, and keeps separate shared memory context for individual workstreams. We have been using projects internally for a while now and it’s a game changer for doing real work, at work. Hat tip to @_andychung, @cleerview, @pklada, @lizeyao and many more for the massive effort from many angles. 🫡
Pete Lada retweeted
“Open weights strengthen competition and competition is what keeps the benefits of AI broadly shared rather than concentrated in the hands of few”. We believe this strongly at @perplexity_ai and are co-signing this letter, with @nvidia! Thanks to @a16z for putting this together!
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
images.nvidia.com/pdf/Open-W…
Pete Lada retweeted
We’re open sourcing WANDR.
WANDR is an internal benchmark we built and used for building deep and wide research capabilities inside Perplexity Computer.
research.perplexity.ai/artic…
