Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for Perplexity for the week ending September 4, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: A psychedelic 1960s Fillmore-style screen-printed gig poster of a wise owl perched on a stack of open books, its eyes spiraling into concentric op-art rings that bloom outward across the page while a glowing question-mark feather melts into a cursor and autumn leaves, bold hand-lettered 'Perplexity' arcing across the top in flowing legible psychedelic type, electric magenta, acid orange, deep teal, and lime green ink layers on cream paper stock with visible registration offset and an ornate border of harvest moons and swirling citation ribbons. Vertical poster composition, intricate linework, flat ink layers, no photorealism.
This Week in Perplexity News
Summary by Claude Sonnet 5.5 based on this week’s links:
- Frontier models land in Computer: Perplexity added Claude Fable 5.1 to Perplexity Computer for Pro and Max subscribers, saying it topped the August WANDR evaluation at 0.601 and $12.76 per task. Days later it reported that GPT-6 Astra scored 0.682 at $11.98 per task, the highest of any model it tested, and Srinivas said Astra is coming to Computer for Pro and Max users soon.
- Cheaper models do the legwork: Srinivas said Computer uses Fable as an orchestrator for high-stakes tasks while GPT 5.6 (Terra) models act as cost-efficient subagents. The Agent API now offers 42 models, including open-weight GLM 5.3, with a one-field switch and fallbacks if a model becomes unavailable.
- Search claims and computer use: Perplexity's Search API took the top positions on the Artificial Analysis Search Index across all three context sizes. Srinivas also said Astra is strong at computer use and will come to Comet and the cloud browser sandbox behind Computer, with evals to follow.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to Perplexity
Astra is also awesome at computer use. We will be bringing it to Comet, as well as our cloud browser sandbox that powers all Computer usage. Evals coming soon!
https://x.com/AravSrinivas/status/2095625524068634808
42 models are now available through the Perplexity Agent API, including the open-weight GLM 5.3 from @Zai_org. Switch models by changing one field in your request. Add fallbacks to keep your agent running if a model becomes unavailable.
https://x.com/perplexitydevs/status/2094945628426256638
We evaluated GPT-6 Astra on WANDR. It scored 0.682 at $11.98 per task, the highest score of any model we tested. GPT-6-Astra scored 13.5% higher than Fable 5.1 at 6.1% lower cost, and 27.0% higher than Opus 5 at 3.3% higher cost.
https://x.com/perplexity_ai/status/2095620419906830788
Claude Fable 5.1 is now available in Perplexity Computer for Pro and Max subscribers. It ranked first in our August WANDR evaluation at 0.601 and $12.76 per task, a 21% higher score and 37% lower cost than Fable 5.
https://x.com/perplexity_ai/status/2094865042873467261
Fable is the frontier model by a good margin right now. Enjoy it on Perplexity Computer as an orchestrator for high-stakes tasks. Computer still uses GPT 5.6 (Terra) models as cost-efficient subagents while taking advantage of Fable’s frontier planning capabilities.
https://x.com/AravSrinivas/status/2094866503460155700
Optimizing On-Device Inference for Apple Silicon
https://www.perplexity.ai/hub/blog/optimizing-on-device-inference-for-apple-silicon
Perplexity Search debuts on the Artificial Analysis Search Index, with all three context size variants taking top positions on the leaderboard The @perplexity_ai Search API comes with three context settings (low, medium, and high) that control how much extracted content each
https://x.com/ArtificialAnlys/status/2093427938968666138
perplexity is the best at search at any level of compute, agnostic of how much compute the competitors use.
https://x.com/AravSrinivas/status/2093450252317794314
Congrats to @OpenAI on building the industry’s frontier model: GPT-6 Astra. It’s far ahead of every other model on wide and deep research tasks, while also being more cost-effective. We’ll be bringing this model up on Perplexity Computer for all Pro and Max users soon!
https://x.com/AravSrinivas/status/2095621195131695352
open-source RL-as-a-service
https://x.com/AravSrinivas/status/2095354358145892733
Leave a Reply