•twitter15877
listening to
timeline
15877
mentions
tracked
tracked
net sentiment
+24%
4998 positive
9734 neutral
1145 negative
volume & sentiment over time
Sep 30 – Oct 14, 2026 · Daily
sources
most discussed
—
active days
15
mentions
Showing 826–850 of 1145 mentions
-
• twitter 1w negativeWhat's stopping more indie hackers from reaching $10K MRR:? lack of skills, lack of focus, or lack of distribution? What's stopping more indie hackers from reaching $10K MRR:? lack of skills, lack of focus, or lack of distribution?view source ↗
-
• twitter 1w negativeAaron has this very right. We’re just at the beginning of building practical AI agents that solve real problems, especially in the enterprise. Swamp does this right now, and it’s wild what people are able to build (and the pace they can build it.) What’s clear to me is that the future are solutions built for this p… Aaron has this very right. We’re just at the beginning of building practical AI agents that solve real problems, especially in the enterprise. Swamp does this right now, and it’s wild what people are able to build (and the pace they can build it.) What’s clear to me is that the future are solutions built for this problem and this era. It’ll be integrated into and around the existing business systems, but the way it’s done will bear no more than a passing resemblance to anything designed before 2025.view source ↗
-
• twitter 1w negativeTo make your agent produce high-quality output, equip it with a way to check its work. Tests are part of that. Here are some of the ones I think are worth investing in. - Write end-to-end tests that simulate real user flows and act as the ground truth - Use property-based testing to specify what should never happen a… To make your agent produce high-quality output, equip it with a way to check its work. Tests are part of that. Here are some of the ones I think are worth investing in. - Write end-to-end tests that simulate real user flows and act as the ground truth - Use property-based testing to specify what should never happen and generate thousands of test cases that attempt to break those constraints - If replacing a system, compare the old and new versions using randomly selected inputs - Require tests to run quickly and deterministically, which reinforces the agent to retry when the loop is slow or unreliable (the agent may learn to retry, not fix the problem) Example tests say what should happen; properties say what must not.view source ↗
-
• twitter 1w negativePeter Thiel on why zero growth is not a neutral outcome: Thiel pushes back on the precautionary impulse to slow AI. Even if extinction risk probabilities are 5-10%, that doesn't necessarily mean you should always go slower. "If you do nothing, if there is no progress on any dimension, I don't think our societies work… Peter Thiel on why zero growth is not a neutral outcome: Thiel pushes back on the precautionary impulse to slow AI. Even if extinction risk probabilities are 5-10%, that doesn't necessarily mean you should always go slower. "If you do nothing, if there is no progress on any dimension, I don't think our societies work at all." He defines the middle class as people who expect their children to do better than themselves. The intergenerational progressive compact in Western society was built on the assumption of progress—economic, material, health, social. "When that breaks down, I think the whole society starts to derange in very, very strange ways." People implicitly assume the alternative to AI is a zero growth world that will somehow be a peaceful social democratic society. "I don't think that's true. The alternative is also far from neutral." You can never just turn the clock back. The question is not AI versus the status quo. It's AI versus societal breakdown. Thiel: the cure for polarization and extremism is not less progress. It's more.view source ↗
-
• twitter 1w negativeSomeone stole my OpenRouter API key. Only noticed because of errors from my own usage after hitting my spending limit. I looked into the OpenRouter logs and their traces are genuinely so interesting to me that I now proceeded to increase the spending limit. Go ahead, my friend. Someone stole my OpenRouter API key. Only noticed because of errors from my own usage after hitting my spending limit. I looked into the OpenRouter logs and their traces are genuinely so interesting to me that I now proceeded to increase the spending limit. Go ahead, my friend.view source ↗
-
• twitter 1w negativeSynara v1.0.0 Beta is out 🪽 100+ PRs led to the greatest and biggest update Synara has ever had: 🪟 Synara Glass: a modern new look, with new icons and adjustable translucency, blur and opacity. 🤝 Hubs bring a coordinator and up to 8 parallel workers together, with shared memory, linked projects, durable task queues … Synara v1.0.0 Beta is out 🪽 100+ PRs led to the greatest and biggest update Synara has ever had: 🪟 Synara Glass: a modern new look, with new icons and adjustable translucency, blur and opacity. 🤝 Hubs bring a coordinator and up to 8 parallel workers together, with shared memory, linked projects, durable task queues and a versioned Library. ✅ Tasks adds a to-do backlog with notes, priorities and due dates, ready to delegate to a new or existing chat. 📬 Inbox brings today’s tasks, overdue work, approvals, failures, reviews and a daily usage recap together. 👥 Add multiple provider accounts, choose models per account, and keep the right account attached to chats, imports, forks and automations. 🔐 Sign in from Settings, import existing provider profiles, and launch named account commands from Synara’s terminal. 📊 View usage by provider account, expand quota details and choose which usage rings appear in the rail. 🔄 Hand work to another provider in the same conversation, with a clear handoff divider and transferred context. ✍️ Claude can generate commit messages, PR text, branch names and diff summaries. 🧠 Model lists refresh for the account you’re using, including after Claude CLI updates; existing choices stay available if refresh fails. 🔎 Code review brings PRs and issues together, with saved filters, side chats, fullscreen images and direct agent handoffs. 🛠️ Beta Auto-fix CI asks an agent to address failing PR checks, waits for approvals and never merges automatically. 📌 Kanban adds an Attention view, review filters, keyboard reordering, agent controls and direct “Send as goal” actions. 🎯 Goals now support up to 120,000 characters, up from 4,096. 🧭 A customizable workspace rail replaces the classic sidebar, with project and Space shortcuts. 🗂️ Open-chat tabs support drag reordering, working indicators, context menus, bulk closing and keyboard navigation. 🎨 macOS gets adjustable full-window glass; projects get their own icons, emoji and colors. 💤 Snview source ↗
-
• twitter 1w negative"I am concerned about the future of the court." Supreme Court Justice Samuel Alito sits down with @ShannonBream on @FoxNewsSunday to discuss the future of the nation's highest court as some groups on the left call for major changes to the institution. Some Democrats have advocated for adding justices or implementing … "I am concerned about the future of the court." Supreme Court Justice Samuel Alito sits down with @ShannonBream on @FoxNewsSunday to discuss the future of the nation's highest court as some groups on the left call for major changes to the institution. Some Democrats have advocated for adding justices or implementing term or age limits for the Supreme Court.view source ↗
-
• twitter 1w negativeRT @CFchangelog: The Agents SDK now supports the Pi Durable harness for long-running agents. Build resilient agents that survive crashes an… RT @CFchangelog: The Agents SDK now supports the Pi Durable harness for long-running agents. Build resilient agents that survive crashes an…view source ↗
-
• twitter 1w negativeI want to become a hardcore Buffalo Bills fan but I’m worried I’m too late in the game, so I’ve been thinking about jumping out of a plane to elbow drop a table as a way to prove myself. I want to become a hardcore Buffalo Bills fan but I’m worried I’m too late in the game, so I’ve been thinking about jumping out of a plane to elbow drop a table as a way to prove myself.view source ↗
-
• twitter 1w negativeIf you’re using Grok Bot, Dots, Muse, or Hermes, your agent is capable of WAY more than you think You’re probably only getting 1% power out of it The best strategy for getting way more done is the ‘reverse prompting loop’ Step 1: Give this reverse prompt: “Based on what you know about me and my work, what are 5 prod… If you’re using Grok Bot, Dots, Muse, or Hermes, your agent is capable of WAY more than you think You’re probably only getting 1% power out of it The best strategy for getting way more done is the ‘reverse prompting loop’ Step 1: Give this reverse prompt: “Based on what you know about me and my work, what are 5 productive things you could do for me?” Step 2: Choose 1 of them Step 3: Do this over and over again until you have a ton of work done You’ll not only be ridiculously productive, you’ll also get tasks done you’ll never think your agent could do This becomes more powerful with the more data sources you have, especially the email connector I hate being in my email. Running this loop usually takes care of all my unread emails Try this out and let me know what you think!view source ↗
-
• twitter 1w negativeStop writing every Hermes agent role from scratch. @Teknium has a collection of 68 ready-made profiles. Pick one around the work you need done: → Spock: investigate why something broke → Data: analyze a dataset → Picard: weigh a difficult decision → Worf: review security risks → Quark: pressure-test your pricing My … Stop writing every Hermes agent role from scratch. @Teknium has a collection of 68 ready-made profiles. Pick one around the work you need done: → Spock: investigate why something broke → Data: analyze a dataset → Picard: weigh a difficult decision → Worf: review security risks → Quark: pressure-test your pricing My starting point: give Spock one recurring bug and ask for evidence, competing explanations, and a way to test each. These profiles supply instructions and configuration—not a new model or guaranteed expertise. Which job would you try first? Spotted via @HermesWatcher. Repo + setup below.view source ↗
-
• twitter 1w negativeAngel Reese going to work for the @AtlantaDream 😤 The steal. The rebound. The bucket through contact. Atlanta battling New York in Game 1 of the WNBA Semifinals on ABC! https://t.co/kefGgkXvNt Angel Reese going to work for the @AtlantaDream 😤 The steal. The rebound. The bucket through contact. Atlanta battling New York in Game 1 of the WNBA Semifinals on ABC! https://t.co/kefGgkXvNtview source ↗
-
• twitter 1w negative@BlockedPaths @AlexanderMann @TacticaLJes I mean you can't really tell people you hate a product because you were banned from their discord and not expect peoples to find you biased for reasons of personal anger @BlockedPaths @AlexanderMann @TacticaLJes I mean you can't really tell people you hate a product because you were banned from their discord and not expect peoples to find you biased for reasons of personal angerview source ↗
-
• twitter 1w negativeAngel Reese won't be denied 😤 https://t.co/NK1R2maBQY Angel Reese won't be denied 😤 https://t.co/NK1R2maBQYview source ↗
-
• twitter 1w negativeIf you’re lacking motivation right now, watch this. This was 5 days after I first launched my app. That was only 6 months ago. If you can see it and believe it, it will happen. Believe in your self and fuck what anyone thinks. https://t.co/wlOfYXLREQ If you’re lacking motivation right now, watch this. This was 5 days after I first launched my app. That was only 6 months ago. If you can see it and believe it, it will happen. Believe in your self and fuck what anyone thinks. https://t.co/wlOfYXLREQview source ↗
-
• twitter 1w negativeIs iterative DPO more effective than GRPO when all outcomes in a sampled group are misaligned? When training on exceptionally novel problems, GRPO can receive little to no learning signal if all sampled outcomes receive identical rewards, resulting in near-zero policy updates. In such cases, could more selective, ite… Is iterative DPO more effective than GRPO when all outcomes in a sampled group are misaligned? When training on exceptionally novel problems, GRPO can receive little to no learning signal if all sampled outcomes receive identical rewards, resulting in near-zero policy updates. In such cases, could more selective, iterative DPO, with carefully constructed preference pairs, provide a more effective learning signal and help the model escape this failure mode?view source ↗
-
• twitter 1w negativeMissouri jumps 11 spots to No. 14 with a win over the Gators 👀 Here's the full AP Top 25 for Week 6 📊 https://t.co/7SEKE0iNrN Missouri jumps 11 spots to No. 14 with a win over the Gators 👀 Here's the full AP Top 25 for Week 6 📊 https://t.co/7SEKE0iNrNview source ↗
-
• twitter 1w negativeStaying comfortable is far more dangerous than failing while trying to build something real. Once you realize the safe path isn’t what you want anyway, taking the risk becomes easy. Bet on yourself every single day. #mindset #success #goals https://t.co/ppv4q6SQpZ Staying comfortable is far more dangerous than failing while trying to build something real. Once you realize the safe path isn’t what you want anyway, taking the risk becomes easy. Bet on yourself every single day. #mindset #success #goals https://t.co/ppv4q6SQpZview source ↗
-
• twitter 1w negativeto anyone saying the skill is trash before even trying it: @CFCA19B https://t.co/7YDybMbtwI to anyone saying the skill is trash before even trying it: @CFCA19B https://t.co/7YDybMbtwIview source ↗
-
• twitter 1w negativeA positive attitude does not mean pretending that problems do not exist. It means seeing the difficulty clearly while still believing there is something you can do about it. It looks for the lesson, the next step, and the opportunity to respond well. Optimism is strongest when it is paired with responsibility and act… A positive attitude does not mean pretending that problems do not exist. It means seeing the difficulty clearly while still believing there is something you can do about it. It looks for the lesson, the next step, and the opportunity to respond well. Optimism is strongest when it is paired with responsibility and action.view source ↗
-
• twitter 1w negativewow Linkstore is doing numbers already!! 😭🤯 just couple of hours since launch and we're already at: → 26 signups → 3 new apps released → 13 new being reviewed submit your webapp now for FREE!! https://t.co/kOR906rzM3 wow Linkstore is doing numbers already!! 😭🤯 just couple of hours since launch and we're already at: → 26 signups → 3 new apps released → 13 new being reviewed submit your webapp now for FREE!! https://t.co/kOR906rzM3view source ↗
-
• twitter 1w negativeChrista Pike has remained unconscious and on a ventilator at a hospital in the four days since her failed execution in Tennessee, and her prognosis might not be known for days more, one of her lawyers said Sunday. https://t.co/nwqu22eaMF Christa Pike has remained unconscious and on a ventilator at a hospital in the four days since her failed execution in Tennessee, and her prognosis might not be known for days more, one of her lawyers said Sunday. https://t.co/nwqu22eaMFview source ↗
-
• twitter 1w negativebecause a web app shows you it's broken the second you open it a database shows you three months later, with someone's data gone simon willison says coding agents take extraordinary discipline to use well the code is cheap proving it holds across every edge case is where the months go because a web app shows you it's broken the second you open it a database shows you three months later, with someone's data gone simon willison says coding agents take extraordinary discipline to use well the code is cheap proving it holds across every edge case is where the months goview source ↗
-
• twitter 1w negativebug fixes & performance improvements bug fixes & performance improvementsview source ↗
-
• twitter 1w negativeWow. This is horrifying. The false rape allegation epidemic is much worse than we realized. Wow. This is horrifying. The false rape allegation epidemic is much worse than we realized.view source ↗