•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 14201–14225 of 15877 mentions
-
• twitter 1w neutralBuild your own MCP server on Supabase! https://t.co/EL1C3Sh60g https://t.co/8uaDK8NjjW Build your own MCP server on Supabase! https://t.co/EL1C3Sh60g https://t.co/8uaDK8NjjWview source ↗
-
• twitter 1w neutralModels in distress will make weird decisions Models in distress will make weird decisionsview source ↗
-
• twitter 1w neutralRT @covacut: i was speaking to a musician friend who had the most interesting reframe of ai i’ve ever heard he said: “ai is you, ai is me,… RT @covacut: i was speaking to a musician friend who had the most interesting reframe of ai i’ve ever heard he said: “ai is you, ai is me,…view source ↗
-
• twitter 1w positiveRecreated a navigation bar prototype I came across online and adapted it to my AgriConnect design. The homepage is the only screen connected so far and still incomplete, but I love how the interaction came together. #ProductDesign #Figma #Prototyping #UXDesign https://t.co/YyZWEtwsUz Recreated a navigation bar prototype I came across online and adapted it to my AgriConnect design. The homepage is the only screen connected so far and still incomplete, but I love how the interaction came together. #ProductDesign #Figma #Prototyping #UXDesign https://t.co/YyZWEtwsUzview source ↗
-
• twitter 1w neutralGet your Sunday back. This is a week where Claude runs the admin and you approve it. Mon 7:00 → the Monday brief: cash, pipeline, everything overdue Daily 9:00 → overdue invoices sorted, reminders drafted Within the hour → every new lead gets a drafted reply After every call → the follow-up, written the same day Thu 1… Get your Sunday back. This is a week where Claude runs the admin and you approve it. Mon 7:00 → the Monday brief: cash, pipeline, everything overdue Daily 9:00 → overdue invoices sorted, reminders drafted Within the hour → every new lead gets a drafted reply After every call → the follow-up, written the same day Thu 12:00 → payroll check: will it clear, and what's due before it Fri 15:00 → client updates drafted from the week's work Last Fri of the month → the month closed: every transaction sorted, every gap flagged Your part is the approving, around 20 minutes a day once it's set up. Sunday stops being admin day. Which slot would you hand over first?view source ↗
-
• twitter 1w positivemuse is starting to slowly pop up in gadget space! nice work! muse is starting to slowly pop up in gadget space! nice work!view source ↗
-
• twitter 1w neutralhttps://t.co/hLHdnCQzbR https://t.co/hLHdnCQzbRview source ↗
-
• twitter 1w positiveRL needs more long-horizon tasks beyond math and coding. @niloofar_mire's team at CMU built an environment for drug design. SMDD-Bench comprises 502 small-molecule design tasks with RDKit, ADMET-AI and Boltz-2 in the loop. The challenges go beyond chemistry: long-horizon planning, exploration, and learning from imperf… RL needs more long-horizon tasks beyond math and coding. @niloofar_mire's team at CMU built an environment for drug design. SMDD-Bench comprises 502 small-molecule design tasks with RDKit, ADMET-AI and Boltz-2 in the loop. The challenges go beyond chemistry: long-horizon planning, exploration, and learning from imperfect feedback are also open problems for RL/ML! SMDD-Bench is available in our Environments Hub, ready to train with prime-rl. Thank you for sharing with the community!view source ↗
-
• twitter 1w neutralSidebar exploration for a productivity app https://t.co/xxBcV18wI4 Sidebar exploration for a productivity app https://t.co/xxBcV18wI4view source ↗
-
• twitter 1w neutralRT @scottcabrinha: I recently joined Prime, and in my first two weeks the sheer velocity and level of execution I've witnessed here are or… RT @scottcabrinha: I recently joined Prime, and in my first two weeks the sheer velocity and level of execution I've witnessed here are or…view source ↗
-
• twitter 1w neutralRT @SpaceX: Teams complete three Falcon launches, four first stage landings at four landing zones in Florida and California, and docking Dr… RT @SpaceX: Teams complete three Falcon launches, four first stage landings at four landing zones in Florida and California, and docking Dr…view source ↗
-
• twitter 1w neutralRT @TurkeyBeaver: @SpaceX is the greatest team on Earth RT @TurkeyBeaver: @SpaceX is the greatest team on Earthview source ↗
-
• twitter 1w neutral#بلا_نقا اللهم رب الحظوظ، رب القلوب، رب الأمل، رب الذين غفلوا عن كل الطرق إلا عنك، رب الذين مات رجاءهم إلا بك، رب الذين مالوا إلا إليك، تولنا فيمن توليت، ولاية نغتني بها ونكتفي، لا يضرنا ضار ولا يمسنا وصب ولا نصب، أنت ولينا في الدنيا والآخرة، وأنت نعم المولى ونعم النصير 📯 #بلا_نقا اللهم رب الحظوظ، رب القلوب، رب الأمل، رب الذين غفلوا عن كل الطرق إلا عنك، رب الذين مات رجاءهم إلا بك، رب الذين مالوا إلا إليك، تولنا فيمن توليت، ولاية نغتني بها ونكتفي، لا يضرنا ضار ولا يمسنا وصب ولا نصب، أنت ولينا في الدنيا والآخرة، وأنت نعم المولى ونعم النصير 📯view source ↗
-
• twitter 1w neutralRT @thirdachilles: https://t.co/mA3zzZdECi RT @thirdachilles: https://t.co/mA3zzZdECiview source ↗
-
• twitter 1w neutralsame sameview source ↗
-
• twitter 1w positive@neke989 Nice! @neke989 Nice!view source ↗
-
• twitter 1w neutralWe are sold out! We are sold out!view source ↗
-
• twitter 1w neutralWhat's your "go" phrase for agents once you've hit alignment? Mine is "Make it happen." What's your "go" phrase for agents once you've hit alignment? Mine is "Make it happen."view source ↗
-
• twitter 1w positiveI don’t think anyone is playing fully vibe coded games. They’re not watching fully vibe coded movies either. We did some research on this: Most people’s choice of playing games or watching movies is socially driven (hence IMDb scores). The tools have been here for a bit. A little AI use is okay, but if you use it en… I don’t think anyone is playing fully vibe coded games. They’re not watching fully vibe coded movies either. We did some research on this: Most people’s choice of playing games or watching movies is socially driven (hence IMDb scores). The tools have been here for a bit. A little AI use is okay, but if you use it end to end it seems like nobody cares for it. This is more true in preference domains like art/games/movies rather than utility ones like code.view source ↗
-
• twitter 1w neutralReality's collapsing in Manhattan. Fight for humanity in CONTROL Resonant now: https://t.co/8EDuChmUrK https://t.co/OXOuFK6SOr Reality's collapsing in Manhattan. Fight for humanity in CONTROL Resonant now: https://t.co/8EDuChmUrK https://t.co/OXOuFK6SOrview source ↗
-
• twitter 1w negativebro how tf is a ghost identifier app making $192k/mo 😭👻 https://t.co/4jvJ5oWhB5 bro how tf is a ghost identifier app making $192k/mo 😭👻 https://t.co/4jvJ5oWhB5view source ↗
-
• twitter 1w neutralDevelopers with a normal job: Can you use Claude/Codex freely at work, or does your company restrict AI tools? Developers with a normal job: Can you use Claude/Codex freely at work, or does your company restrict AI tools?view source ↗
-
• twitter 1w neutralshe didn't sleep and cried all night btw she didn't sleep and cried all night btwview source ↗
-
• twitter 1w neutralIMO the only tests you should have in the age of coding agents are, in order of priority: 1. Full E2E tests. Nothing mocked out at all. Can even be something that runs in prod on test accounts via Playwright or equivalent. 2. Integration tests. Agents make more mistakes as things bleed between data/API boundaries wher… IMO the only tests you should have in the age of coding agents are, in order of priority: 1. Full E2E tests. Nothing mocked out at all. Can even be something that runs in prod on test accounts via Playwright or equivalent. 2. Integration tests. Agents make more mistakes as things bleed between data/API boundaries where schemas can drift. 3. Golden tests. This helps ground the code with real examples of data, and can be used as regressions against edge cases. Unit tests are bloat 99% of the time if you’re using a frontier model since they’re smart enough now to get the implementation (and subsequent iterations) right on the first shot, so they only add bloat at this point.view source ↗
-
• twitter 1w positiveDot, Muse, Grok Bot, and Hermes are all EXCELLENT agents They all have their own strengths and weaknesses, so you need to know which to use for each task Here is each agent, and when you should be using them: GROK BOT- best agent for heavy knowledge work Strengths: Because you can create many different agents with … Dot, Muse, Grok Bot, and Hermes are all EXCELLENT agents They all have their own strengths and weaknesses, so you need to know which to use for each task Here is each agent, and when you should be using them: GROK BOT- best agent for heavy knowledge work Strengths: Because you can create many different agents with many different contexts, skills, and memories, you are able to get a wide plethora of work done really really well Weaknesses: Grok 4.7 is a great model, but not frontier. Also not much usage on cheaper plans. Who it's for: People who have a diverse set of responsibilities and tasks they need to get done META MUSE: best agent for getting personal tasks done online Strengths: Lightning fast, free, and by far the best agent at navigating the internet. Can just 'figure it out' for getting tasks done in browsers Weaknesses: Not great at coding. Model is lightning quick, but not the smartest or most creative. Weaker at knowledge work because of this. Who it's for: The best 'personal assistant' agent. Booking reservations, finding flights, filling out forms, unsubscribing from websites. The more 'normie' type use cases. Also it's free. So anyone on a budget. HERMES: Open source, fully customizable, do anything assitant Strengths: Fully open source and customizable. Anything you want to change in the agent, you can just change it. Use any model or subscription. Does almost anything you ask without many guardrails. Also a smaller decentralized team supporting it, so it's always great to support the rebels Weaknesses: No mobile app. Because it's open source and fully customizable, it's not always the most reliable if you tinker too much Who it's for: tinkerers who want full control over their agent. Also great for the local model community and people with their own home AI labs. My Hermes maintains all my networks and equipment for me better than any other agent DOT: Your ultimate AI agent project manager Strengths: The smartest model in the best haview source ↗