@mntruell Michael Truell

Michael Truell posts on X about agents, ai, 3m, css the most. They currently have [------] followers and [--] posts still getting attention that total [-------] engagements in the last [--] hours.

Engagements: [-------] #

Mentions: [--] #

Followers: [------] #

CreatorRank: [-------] #

Social Influence

Social category influence technology brands stocks social networks

Social topic influence agents #449, ai, 3m, css, cascade #48, paint #1361, vm, ultra, for all, future

Top accounts mentioned or mentioned by @cursorai @amanrsanger @thekitze @testingcatalog @theprnvbot @akatzzzzz @michaelaubry @tombuilds @rbouschery @zerou_hamza @tomcocobrico @bitsizejourney @openai @stephenrayner @mikeboysen @scobleizer @jadenitripp @karpathy @paulg @garrytan

Top Social Posts

Top posts by engagements in the last [--] hours

"@bitsizejourney @cursor_ai @OpenAI What does your workflow look like"
X Link 2024-02-16T21:34Z [---] followers, [---] engagements

"@stephen_rayner @cursor_ai What extensions do you have installed Could you send a screenshot"
X Link 2024-12-26T01:43Z [----] followers, [--] engagements

"@mikeboysen @cursor_ai @Scobleizer Apologies about this. DM'ed you Certainly want to fix whatever you ran into"
X Link 2025-01-17T03:12Z [----] followers, [---] engagements

"@jadenitripp @cursor_ai Thank you It seems like a problem with the model (seeing the right tools / well formatted prompt). We're going back and forth with the Gemini team on it"
X Link 2025-03-29T04:19Z [----] followers, [---] engagements

"@thekitze Hey We've been coordinating with the Gemini team on this. It seems like they're about to release a potential improvement"
X Link 2025-04-04T22:39Z [----] followers, [---] engagements

"@karpathy In the next version of Cursor stuffing context will get much easier :D"
X Link 2025-04-25T04:48Z 27.6K followers, 169.5K engagements

"https://www.cursor.com/blog/team https://www.cursor.com/blog/team"
X Link 2025-05-19T04:49Z 22.6K followers, 20.9K engagements

"More than anyone else YC and @paulg made starting a company legible to me and my cofounders. Was an honor to sit down with @garrytan and the latest batch Michael Truell (@mntruell) co-founder and CEO of Anysphere the company behind @Cursor_ai joined @garrytan to talk about building one of the fastest-growing startups of all timeand why he's betting everything on a world beyond code. He walks through the early insights that https://t.co/ZRNtIR8MCi Michael Truell (@mntruell) co-founder and CEO of Anysphere the company behind @Cursor_ai joined @garrytan to talk about building one of the"
X Link 2025-06-11T22:57Z 32.7K followers, 139.4K engagements

"@johnyeo_ @supportingden Do you trust it roughly as much as a person"
X Link 2025-08-11T01:15Z 32.4K followers, 16.5K engagements

"Some of Cursor's early team"
X Link 2025-05-19T04:49Z 37K followers, 481.2K engagements

"When will we be able to add AI coworkers to Slack to help take on misc operational work Updating spreadsheets creating channels running "cron job" business workflows conducting Deep Research/Operator-style tasks. Same API as a human (bidirectional DM's calls shared links) with persistent memory/personality and access to all your team's tools"
X Link 2025-08-11T01:12Z 36.7K followers, 428.5K engagements

"After adopting Cursor businesses merge 40% more PRs each week. New economics research from the University of Chicago. Who uses AI agents How do agents impact output How might agents change work patterns New working paper studies usage + impacts of coding agents (1/n) https://t.co/bw76w7we74 Who uses AI agents How do agents impact output How might agents change work patterns New working paper studies usage + impacts of coding agents (1/n) https://t.co/bw76w7we74"
X Link 2025-11-12T23:45Z 38.1K followers, 215.5K engagements

"We rebuilt how our agent uses context. Instead of stuffing everything into a prompt Cursor dynamically discovers context via files tools and history cutting token usage by 46.9% and freeing up more space for the agent to work. Cursor's agent now uses dynamic context for all models. It's more intelligent about how context is filled while maintaining the same quality. This reduces total tokens by 46.9% when using multiple MCP servers. https://t.co/PhBkV6foum Cursor's agent now uses dynamic context for all models. It's more intelligent about how context is filled while maintaining the same"
X Link 2026-01-07T06:52Z 53.1K followers, 257.2K engagements

"@mckaywrigley We think of Cursor as a desktop app not an IDE. Agree the ideal Cursor becomes a dashboard for working with agents"
X Link 2026-01-07T20:07Z 42.6K followers, 50.3K engagements

"@carboxydev Agree Very curious how much better these can be made too. File graphs feel far from the optimal visualization of a codebase"
X Link 2026-01-18T10:11Z 53.2K followers, 16.9K engagements

"Lots more to figure out but perhaps a glimpse at the not-too-distant future. One concrete data point: a critical isolated component of an upcoming launch was fully written by one of these agent grind sessions. It finished overnight and wouldve taken roughly an engineer-month circa 2023"
X Link 2026-01-19T21:15Z 53.4K followers, 26.2K engagements

"@mohii The Ultra plan comes with lots of included usage and hope to have more to share there soon :)"
X Link 2026-02-10T20:08Z 57.5K followers, [----] engagements

"@testingcatalog Opus"
X Link 2026-02-10T20:09Z 57.5K followers, [----] engagements

"@thePrnvBot Local models are really tricky and constraining Why not remote (Perhaps you can run Qwen-30B-A3B or GLM-4.5-Air on a very powerful personal computer)"
X Link 2026-02-10T20:14Z 57.5K followers, [----] engagements

"@nikku696969 Big one before the end of the month :)"
X Link 2026-02-10T20:17Z 57.8K followers, 14.3K engagements

"@xameyz Yes :)"
X Link 2026-02-10T20:45Z 57.5K followers, [----] engagements

"We built a new agent harness that orchestrates thousands of coding agents stays "fresh" over long runs and converges despite errors & contention. Peaked at [----] commits/hour over a week. We've been working on very long-running coding agents. In a recent week-long run our system peaked at over [----] commits per hour across hundreds of agents. We're sharing our findings and an early research preview inside Cursor. https://t.co/Xo76WER6L1 We've been working on very long-running coding agents. In a recent week-long run our system peaked at over [----] commits per hour across hundreds of agents."
X Link 2026-02-05T19:00Z 58.3K followers, 331.7K engagements

"Will be doing an AMA tomorrow at noon PT Will try to answer as much as I can about Cursor models AI coding etc"
X Link 2026-02-09T20:26Z 58.3K followers, 24K engagements

"Nope Our goal is to build the best way to code with AI and we'd like to stay very focused on that (e.g. we don't serve Tab outside of our product). That said we are excited about creating more powerful APIs for hooking into Cursor in the near future. https://x.com/DanielWhit21874/status/2020959934255620477 @mntruell Would be quite interesting to watch have a question @mntruell are you planning to release composer [--] through the public API at some point 👀 https://x.com/DanielWhit21874/status/2020959934255620477 @mntruell Would be quite interesting to watch have a question @mntruell are you"
X Link 2026-02-10T20:12Z 58.3K followers, 24.8K engagements

"We've been delightfully surprised to see that pull requests from long-running agents have higher merge rates while being an order of magnitude more ambitious. Long-running agents are now available at https://t.co/3PT8c7azU3 for Ultra Teams and Enterprise plans. With our new harness agents can complete much larger tasks. https://t.co/7p57WeR04t https://t.co/pGePEFRPTT Long-running agents are now available at https://t.co/3PT8c7azU3 for Ultra Teams and Enterprise plans. With our new harness agents can complete much larger tasks. https://t.co/7p57WeR04t https://t.co/pGePEFRPTT"
X Link 2026-02-17T18:25Z 58.3K followers, 26.5K engagements

"How do you think we should be pricing for very expensive models (o3) or ultra-long context windows (100k LOC) in Cursor API pricing higher subscription tier something else"
X Link 2025-05-06T20:45Z 58.3K followers, 549.5K engagements

"A conversation with @patrickc on old programming languages software at industrial scale and AI's effect on economics/biology/Patrick's daily life. 00:15 - Why Patrick wrote his first startup in Smalltalk 03:35 - LISP chatbots 06:09 - Good ideas from esoteric programming languages 09:12 - Brett Victor and Dynamicland 16:37 - Programming human organizations 20:28 - A codebase's "Big Bang" moment and MongoDB 25:49 - Rewriting Stripe 32:00 - How do you Patrick Collison use AI 38:25 - Changes to GDP/TFP 41:56 - Programming human biology 46:10 - Unexpected beneficiaries of AI"
X Link 2025-07-15T17:15Z 58.3K followers, 353K engagements

"A conversation with @johnschulman2 on the first year LLMs could have been useful building research teams and where RL goes from here. 00:20 - Speedrunning ChatGPT 09:22 - Archetypes of research managers 11:56 - Was OpenAI inspired by Bell Labs 16:54 - The absence of value functions 18:23 - Continual learning 21:09 - Brittle generalization 24:05 - Co-training generators and verifiers GANs 27:06 - Johns personal use of AI for research 28:54 - Day in the life 33:01 - Slowdowns in consequential ML ideas 36:21 - "Peer review" within the labs 39:19 - Distribution shift in researchers 43:33 - Future"
X Link 2025-12-17T22:21Z 58.3K followers, 590.1K engagements

"Cursor seeks to be the best and most powerful way to code with AI. What are the ways in which we could be better"
X Link 2026-01-07T19:39Z 58.3K followers, 257K engagements

"John Schulman on creating TRPO"
X Link 2026-01-08T13:01Z 58.3K followers, 52.2K engagements

"How would you like to hack or extend Cursor What does a perfectly extensible coding agent look like to you"
X Link 2026-01-09T13:38Z 58.3K followers, 72.9K engagements

"We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing CSS cascade layout text shaping paint and a custom JS VM. It kind of works It still has issues and is of course very far from Webkit/Chromium parity but we were astonished that simple websites render quickly and largely correctly. GPT-5.2 Codex is now available in Cursor We believe it's the frontier model for long-running tasks. GPT-5.2 Codex is now available in Cursor We believe it's the frontier model"
X Link 2026-01-14T22:12Z 58.3K followers, 6.4M engagements

"Excited to continue stress testing the boundaries of coding agents and report back on what we learn. Code here: https://github.com/wilsonzlin/fastrender https://github.com/wilsonzlin/fastrender"
X Link 2026-01-14T22:12Z 58.3K followers, 230.5K engagements

"More on our experiments here: https://cursor.com/blog/scaling-agents https://cursor.com/blog/scaling-agents"
X Link 2026-01-14T22:12Z 58.3K followers, 205.2K engagements

"Watch Cursor build a 3M+ line browser in a week We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing CSS cascade layout text shaping paint and a custom JS VM. It kind of works It https://t.co/jA6wDdwRif We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing CSS cascade layout text shaping paint and a custom JS VM. It"
X Link 2026-01-18T09:54Z 58.3K followers, 1.6M engagements

"A tiny piece of polish: Cursor CLI now supports word-level inline diffs"
X Link 2026-01-19T14:12Z 58.3K followers, 48.1K engagements

"Our tips on how to use Cursor: - Start with a plan (Shift+Tab Plan Mode) - Let Cursor search on its own don't over-tag context - Use tests as the feedback loop (TDD + iterate until green) - When it goes sideways: revert tighten the plan rerun - Keep long chats short; use @ Past Chats for continuity - Add lightweight .cursor/rules for recurring mistakes - Use skills + hooks for long-running "grind until tests pass" loops - Run multiple agents/models in parallel via worktrees Here's what we've learned from building and using coding agents. https://t.co/PuBtYuhyhd Here's what we've learned from"
X Link 2026-01-20T15:37Z 58.3K followers, 364.4K engagements

"Cursor now uses a swarm of agents. It's faster can work for longer and keeps context clean. Cursor now uses subagents to complete parts of a task in parallel. Subagents lead to faster overall execution and better context usage. They also let agents work on longer-running tasks. Also new: Cursor can generate images ask clarifying questions and more. https://t.co/LTsxuaYuoU Cursor now uses subagents to complete parts of a task in parallel. Subagents lead to faster overall execution and better context usage. They also let agents work on longer-running tasks. Also new: Cursor can generate images"
X Link 2026-01-22T22:49Z 58.3K followers, 146.2K engagements

"Part of our efforts to get reliable long-running agents to everyone https://x.com/mntruell/status/2011562190286045552 We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing CSS cascade layout text shaping paint and a custom JS VM. It kind of works It https://t.co/jA6wDdwRif https://x.com/mntruell/status/2011562190286045552 We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week. It's 3M+ lines of code across thousands of files. The"
X Link 2026-01-22T22:49Z 58.3K followers, 10.8K engagements

"Excited for skills in Cursor Agent Skills are now available in Cursor. Skills let agents discover and run specialized prompts and code. https://t.co/aZcOkRhqw8 Agent Skills are now available in Cursor. Skills let agents discover and run specialized prompts and code. https://t.co/aZcOkRhqw8"
X Link 2026-01-23T19:41Z 58.3K followers, 68.8K engagements

"It's a really great model Every Cursor team member who tested it found it noticeably better than Opus [---]. Opus [---] is now available in Cursor It's highly effective at long-running tasks and reviewing code. Opus [---] is now available in Cursor It's highly effective at long-running tasks and reviewing code"
X Link 2026-02-05T19:03Z 58.3K followers, 87K engagements

"Answering questions in this thread for the next [--] minutes Feel free to ask anything about Cursor models long-running agents AI coding etc. Sualeh / Aman may join as well"
X Link 2026-02-10T20:07Z 58.3K followers, 120.7K engagements

"Thanks for all the questions We'll continue answering some of these async as well"
X Link 2026-02-10T20:57Z 58.3K followers, 12.7K engagements

"You can now easily give Cursor access to your knowledge bases deployment environments observability suite internal tools and design files. Ask it to figure out an error by scanning through Datadog hunt down runbooks in Notion deploy to AWS or replicate a mock from Figma. Much of this was possible before but it was too hard. Now it feels like installing an app You can configure plugins for your whole team too. Extend Cursor with plugins now available in our marketplace. https://t.co/5lMEi9jath Extend Cursor with plugins now available in our marketplace. https://t.co/5lMEi9jath"
X Link 2026-02-17T18:47Z 58.3K followers, 74.7K engagements

"Extend Cursor with plugins now available in our marketplace"
X Link 2026-02-17T18:32Z 310.1K followers, 398.4K engagements

"Long-running agents are now available at for Ultra Teams and Enterprise plans. With our new harness agents can complete much larger tasks. http://cursor.com/blog/long-running-agents http://cursor.com/agents http://cursor.com/blog/long-running-agents http://cursor.com/agents"
X Link 2026-02-12T20:32Z 310.1K followers, 323.2K engagements

"Thanks for all the questions We'll continue answering some of these async as well"
X Link 2026-02-10T20:57Z 58.3K followers, 12.7K engagements

"@mntruell Would be quite interesting to watch have a question @mntruell are you planning to release composer [--] through the public API at some point 👀"
X Link 2026-02-09T20:36Z [----] followers, 25.5K engagements

"Will be doing an AMA tomorrow at noon PT Will try to answer as much as I can about Cursor models AI coding etc"
X Link 2026-02-09T20:26Z 58.3K followers, 24K engagements

"Opus [---] is now available in Cursor It's highly effective at long-running tasks and reviewing code"
X Link 2026-02-05T17:49Z 310.1K followers, 409K engagements

"We've been working on very long-running coding agents. In a recent week-long run our system peaked at over [----] commits per hour across hundreds of agents. We're sharing our findings and an early research preview inside Cursor"
X Link 2026-02-05T17:00Z 310.1K followers, 787.4K engagements

"Agent Skills are now available in Cursor. Skills let agents discover and run specialized prompts and code"
X Link 2026-01-23T17:34Z 310.1K followers, 582.7K engagements

"Cursor now uses subagents to complete parts of a task in parallel. Subagents lead to faster overall execution and better context usage. They also let agents work on longer-running tasks. Also new: Cursor can generate images ask clarifying questions and more"
X Link 2026-01-22T20:23Z 310.1K followers, 803.3K engagements

"Here's what we've learned from building and using coding agents. https://cursor.com/blog/agent-best-practices https://cursor.com/blog/agent-best-practices"
X Link 2026-01-12T20:28Z 310.1K followers, 451K engagements

"This work by @cursor_ai is I think the coolest AI breakthrough since GPT-4. (And there are plenty of candidates) https://simonwillison.net/2026/Jan/19/scaling-long-running-autonomous-coding/ https://simonwillison.net/2026/Jan/19/scaling-long-running-autonomous-coding/"
X Link 2026-01-19T19:04Z 646.6K followers, 341.9K engagements

"A tiny piece of polish: Cursor CLI now supports word-level inline diffs"
X Link 2026-01-19T14:12Z 58.3K followers, 48.1K engagements

"GPT-5.2 Codex is now available in Cursor We believe it's the frontier model for long-running tasks"
X Link 2026-01-14T18:05Z 310.1K followers, 1.7M engagements

"More on our experiments here: https://cursor.com/blog/scaling-agents https://cursor.com/blog/scaling-agents"
X Link 2026-01-14T22:12Z 58.3K followers, 205.2K engagements

"How would you like to hack or extend Cursor What does a perfectly extensible coding agent look like to you"
X Link 2026-01-09T13:38Z 58.3K followers, 72.9K engagements

"John Schulman on creating TRPO"
X Link 2026-01-08T13:01Z 58.3K followers, 52.2K engagements

Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing