Cofounder, CSO @perplexity_ai. Former high frequency trader, competitive programmer. Think fast, build faster.
New York, NY
Joined December 2011
- Tweets186
- Following284
- Followers23K
- Likes2.4K
At Perplexity we are still hiring across the world, especially in New York. Perplexity was founded remotely and to this day we still believe in finding the best people wherever they are. Agency and ownership over location.
Tech jobs are concentrating in the Bay Area
15% of all open tech roles are now in the Bay Area, about one in seven and a record high.
It’s even more concentrated for product roles. One in four open PM and design roles is in the Bay Area, and one in five engineering roles. All three are at or near record highs, and each has nearly doubled its share since 2022.
Meanwhile, remote roles keep shrinking. Just 14% of open tech roles offer a remote option, the lowest on record and down from 21% in late 2022.
Remote share by role:
• Engineering: 14%, down from 25%
• Design: 19%, down from 34%
• PM: steady at about 21% for two years, still near its low
Put it all together: sometime last year, open PM, eng, and design roles in the Bay Area overtook remote roles worldwide. Three years ago, remote led almost 2 to 1.
Teammates are now available in Perplexity's Mac app, allowing you to bridge your local and cloud environments. Our goal is to upgrade the Mac app over time to be a collaborative workspace for you, your agents, and your coworkers. A persistent workspace you can do all of your work in: orchestrate all of your agents seamlessly with as little context switching as possible.
The team is working hard day to day to improve performance, quality, and features until it is the goto destination for all of your day to day work.
Try the latest at perplexity.ai/platforms
4
446
SemiAnalysis is a heavy power user of Perplexity in Slack.
Perplexity in Slack uses the latest frontier models to bridge surfaces where you already work: Slack, Github, Google Workspace, and more. This allows you to centralize all of your work in one place rather than have to jump around a bunch of interfaces.
Perplexity in Slack is primarily driven by explicit tags: explicit is better than implicit, especially in a noisy environment like Slack where human attention is the bottleneck. An important principle at Perplexity is that agents should minimize context switching and respect human attention, which is the bottleneck in most knowledge work today. We also value full transparency: each agent says exactly who created it and links back to the session that created it.
It's important to us that we continue to design our products to be high signal as we scale up Perplexity teammates as workplace agents.
The frontier changes quickly - the WANDR record from Fable 5.2 only lasted one day. Driven by a 60% cost reduction from Gemini 4 Carbon.
Gemini 4 Carbon is now available in Perplexity Computer for Pro and Max subscribers, and in Search for Max subscribers.
It scores 0.857 on our WANDR benchmark at $5.86 per task, matching Claude Fable 5.2 at 40% of the cost.
ALT WANDR score versus cost per task. Gemini 4 Carbon scores 0.857 at $5.86 per task, on the Pareto frontier. Claude Fable 5.2 scores 0.851 at $14.51 per task, and Gemini 4 Argon scores 0.802 at $7.88 per task.
Knowledge work is doing just as well as ever. A lot more fun and efficient with AI automating the tedious parts as well.
The frontier continues to advance. A huge jump from Fable 5.1's 68% score to 85%.
Claude Fable 5.2 is now available in Perplexity Computer for Pro and Max subscribers, and in Search for Max subscribers.
On our WANDR benchmark, it achieved Pareto frontier of performance and efficiency, with a record score of 0.851 at $14.51 per task.
ALT Updated WANDR score versus cost per task chart. Claude Fable 5.2 scores 0.851 at $14.51 per task. Claude Fable 5.1 scores 0.684 at $13.16 per task following a rerun. Fable 5.2 lies on the performance-cost Pareto frontier.
The entire frontier is available in Perplexity today. perplexity.ai/platforms
4
1,001
At Perplexity, agent prompts are no longer typed by humans: increasingly teammates are prompting each other, listening to automations, and ambiently listening to human feedback. Perplexity bridges the context between a large number of cloud tools and software services: searching and processing more than a human could possibly track manually. Hard decisions, restraint, and judgment before shipping are of course still enforced by humans.
A particularly important value at Perplexity is to always seek the truth. In today's stack, this means centralizing the ground truth in git repos and data warehouses when answering questions about the business, instead of looking at intermediate, often inaccurate or outdated artifacts. This is what enterprise cloud agents like Perplexity are especially good at: connecting the dots across your organization and monitoring the facts 24/7.
Even as an AI-native company it took us many months of development and cultural transformation to get to this point. It will be fascinating what the world looks like when all businesses reach this level of automation and beyond.
Today we are rolling out the latest form factor for work: Perplexity teammates. Agents have reached the point where they can start to be trusted with responsibilities at work. Teammates excel at automating tasks like deep research, data analysis, QA, triaging tickets, and reviewing code, which has saved each of us internally at Perplexity hundreds of hours of menial work. Leaving us the much more interesting work of setting vision, judging quality, and teaching restraint.
Agents are now rising up beyond tools and task-based sessions to take on supporting and coworking roles. Teammates proactively reach out to you, other coworkers, and other teammates in the workspace. Teammates close the loop on their own work, finishing the job instead of requiring repeated steering or manual management of sessions.
Available to Max users as a research preview today.
Automate ad agencies with Computer. Save time so you can focus on the hard problems that aren't yet solved by AI, like positioning and creativity.
Computer managed $30k in Meta ad spend for Get Maine Lobster, outperforming their agency.
Compared to their usual ads, Computer delivered 3.5x revenue with 63% higher ROAS. It automated creative analysis, ad production, and media buying.
Read more: pplx.ai/gml
This level of attention to detail is not yet solved by AI (for now).
Tell Claude to implement these 3 concepts to instantly make your platformer feel fantastic
Each one quietly forgives a mistake the player never notices making
1 Coyote time
Players often press jump a moment after running off a ledge. To them they were still on it. A basic controller ignores that press and they fall, and it feels like the game cheated. Let the jump still work for about 6 frames (0.1s) after leaving the ground
2 Jump buffering
When chaining jumps, players press jump just before they land. A basic controller throws that press away, so the character lands and stands still. Keep the press for about 6 frames and fire the jump on the frame they touch down
3 Corner correction
A jump that misses a ledge by a few pixels hits the wall and slides down, even though it looked like it made it. If the feet are 4 px or less under the ledge top, nudge the player up onto it. The same trick works for a head clipping a ceiling corner
Each one is under 10 lines of code but makes a huge difference
16
4,825
Props to @pika_labs for supporting the open weights ecosystem. Now the top open weight model for text to video.
Meet Pika H3 Flex, debuting today as the #1 open weight model on DesignArena’s t2v board.
It’s built for professional iteration, with exportable audio stems, resolutions up to 4k, and faster-than-realtime generation. It can produce a 15-second clip with soundtrack in as little as 7 seconds.
So, yeah. It’s kind of a flex 💅
The hard part of security work still requires human ingenuity.
Just dropped a new blog post! 🔥
blog.orange.tw/posts/2026-10…
Voice is the ultimate UI/UX for orchestration - spawn as many agents as you need all from one click.
An incredible result. Worth noting the great storytelling and presentation here to make the significance of the work understandable by everyone.
Impressive new results from Argon, now available in Perplexity. The frontier and cost/quality tradeoff is extremely close between the top models.
Gemini 4 Argon is a frontier model and has set a new SoTA on Wide-And-Deep-Research (WANDR) benchmark. Available now to all Perplexity users both on fast search and Computer (agent) modes.
5
33
7,570