# Perplexity Published articles for Perplexity. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Perplexity's AI agents helped build a database. They weren't allowed to run it. DevFeed: [Perplexity's AI agents helped build a database. They weren't allowed to run it.]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-16T21:51:15Z Content type: article Language: en Sources: [The New Stack]() Topics: [Database](), [DynamoDB](), [Rust](), [Artificial Intelligence](), [rocksdb](), [Amazon S3]() Tags: [agents](), [ai](), [ai-agents](), [ai-infrastructure](), [api](), [coding](), [coding-agents](), [database](), [databases](), [dynamodb](), [open-source](), [performance](), [perplexity](), [rocksdb](), [rust](), [s3]() ### AI overview Perplexity built CobbleDB, a Rust key-value store, after finding DynamoDB too costly and insufficiently controllable for its search workload. Coding agents helped develop it, but were not allowed to run it in production. Perplexity measured lower read latency and expects lower costs, with plans to open-source the database. ### Source excerpt Perplexity decided it was paying too much for DynamoDB and wasn't getting the control it wanted over read performance. So The post Perplexity's AI agents helped build a database. They weren't allowed to run it. appeared first on The New Stack. ## Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation DevFeed: [Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation]() Original publisher: [Read original article]() Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Apple Machine Learning Research]() Topics: [text-generation](), [Algorithms](), [Language models](), [Inference]() Tags: [inference](), [language-models](), [performance](), [perplexity](), [research](), [text-generation](), [tokens]() ### AI overview The article introduces Trajectory-Shaped Discrete Flow Matching, a training method that guides intermediate trajectory decisions with an energy-based coherence measure. The authors argue that poor distillation trajectories, rather than insufficient student capacity, limit few-step generation. On a 170M-parameter language-modeling task, an 8-step student reportedly achieves lower perplexity than a 1,024-step teacher while reducing inference steps. ### Source excerpt Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to train a student to reproduce the process in a few steps. When the student underperforms, the usual explanation is insufficient capacity. We argue the opposite: the trajectory is the bottleneck, not the student. Each training trajectory is built through a chain of blind stochastic jumps with no evaluation of sequence quality; a single bad decision at an early midpoint propagates through subsequent steps... ## How to opt out of AI chatbot training DevFeed: [How to opt out of AI chatbot training]() Original publisher: [Read original article]() Author: Pieter Arntz Published: 2026-09-15T15:41:44Z Content type: tutorial Language: en Sources: [Malwarebytes]() Topics: [ChatGPT](), [OpenAI](), [online privacy](), [Artificial Intelligence]() Tags: [ai](), [anthropic](), [chatgpt](), [how-to](), [human-review](), [news](), [openai](), [perplexity](), [privacy](), [privacy-filter]() ### AI overview This tutorial explains how to turn off ChatGPT's "Improve the model for everyone" setting to opt out of using chats for model improvement. It also notes that authorized personnel and trusted service providers may still access content for safety, support, troubleshooting, security, abuse investigations, or legal matters. ### Source excerpt ChatGPT contractors are reviewing real users' conversations. Here's how to stop AI companies using your chats for model training. ## Your robots.txt Says Yes. Your Firewall Says 403. DevFeed: [Your robots.txt Says Yes. Your Firewall Says 403.]() Original publisher: [Read original article]() Author: Brent Leekley Published: 2026-06-11T00:00:00Z Content type: article Language: en Sources: [brent.leekley.me blog]() Topics: [Cloudflare](), [AI Bots](), [AI search](), [Crawler](), [Firewall]() Tags: [403](), [aeo](), [ai-bots](), [ai-crawl-control](), [ai-crawlers](), [ai-search](), [ai-visibility](), [blocking](), [bot-management](), [chatgpt-user](), [cloudflare](), [firewall](), [gptbot](), [oai-searchbot](), [perplexity](), [robots](), [robots-txt]() ### AI overview A field note explains how a Cloudflare AI-bot blocking setting returned 403 responses to all AI agents even though the site's robots.txt allowed AI search and blocked training crawlers. It distinguishes training crawlers, search indexers, and user-triggered fetchers, and recommends auditing enforcement at the firewall layer. ### Source excerpt A client's robots.txt welcomed AI search and blocked training crawlers, but Cloudflare's blunt AI-bot toggle was returning 403 to every AI agent at the edge. How the block was found, the AI Crawl Control fix, and why you should audit enforcement, not intent. ## Perplexity CEO Aravind Srinivas on building an answer engine for curiosity DevFeed: [Perplexity CEO Aravind Srinivas on building an answer engine for curiosity]() Original publisher: [Read original article]() Author: Alia Fite Published: 2024-06-26T00:00:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Conversational AI](), [Artificial Intelligence](), [Large Language Model](), [Natural language processing](), [App](), [Wiki](), [Google]() Tags: [ai](), [app](), [ceo](), [conversational-ai](), [learning](), [llms](), [natural-language-processing](), [perplexity](), [search](), [slackbot](), [web](), [wikipedia]() ### AI overview Figma interviews Perplexity co-founder and CEO Aravind Srinivas about the company's vision for an answer engine that synthesizes information from the web. He discusses conversational search, sourcing, curiosity, and the origins of Perplexity as an internal Slackbot. ### Source excerpt Co-founder and CEO Aravind Srinivas wants Perplexity to be not only a resource, but an engine for curiosity. ## Air Around AI (a3) #5 DevFeed: [Air Around AI (a3) #5]() Original publisher: [Read original article]() Author: Pradeep Kumar Published: 2024-06-02T19:32:52Z Content type: article Language: en Sources: [Air Around AI]() Topics: [Artificial Intelligence](), [Generative AI](), [Retrieval Augmented Generation (RAG)](), [Large Language Model](), [AI Chat](), [Data Science]() Tags: [ai](), [gen-ai](), [llms](), [perplexity](), [rag](), [using]() ### AI overview This issue of Air Around AI is a roundup covering predictions about AGI, Perplexity's Pages feature, generative AI and deepfakes in elections, comparisons among AI models, Retrieval-Augmented Generation paradigms, financial statement analysis with large language models, exit-poll analysis, and AI-generated shows from Fable's Showrunner. ### Source excerpt Elections and Content from Gen AI, Chatbot Olympics, Create Shows with AI, Exit Polls Science, Perplexity : Pages feature, RAG Paradigms, Read Financial Statements using LLMs