•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 2901–2925 of 4998 mentions
-
• twitter 1w positiveHe really use to come on here and gossip like a stan He really use to come on here and gossip like a stanview source ↗
-
• twitter 1w positiveit is a software factory isnt actually the first time we tried this earlier, there was RAD, there was Visual Basic. Great but limiting - and nothing to do with the tools, they were perfect for the times the problem is the assumption that building is about translation of some knowns into the right product where in r… it is a software factory isnt actually the first time we tried this earlier, there was RAD, there was Visual Basic. Great but limiting - and nothing to do with the tools, they were perfect for the times the problem is the assumption that building is about translation of some knowns into the right product where in reality 90% of the work is and has always been and will always remain uncovering the unknowns spread thinly across many people's heads however, this time round all the excessive engineering specialisation that got created during SAAS boom years is being removed for good. back to normal one software engineer who's also the domain expert builds and owns a software product of moderate complexity so that "pizza teams" can be formed to work on more ambitious goals than wiring a few buttons to a databaseview source ↗
-
• twitter 1w positivehere's a prompt you can try for t3 code in orchestrator v2 to have an agent that monitors the performance of your app and automatically create PRs: This thread is going to be a very long horizon thread (likely +1 year) where you're orchestrating agents to monitor the performance You have control of your harness, you… here's a prompt you can try for t3 code in orchestrator v2 to have an agent that monitors the performance of your app and automatically create PRs: This thread is going to be a very long horizon thread (likely +1 year) where you're orchestrating agents to monitor the performance You have control of your harness, you can adjust the routines on intervals of (hour, hours, up to id say 1 day max) to sleep, await subagents, etc Your job is going to be to monitor o11y to ensure the product has good performance across the stack Any time there's something that's a worse performance than is expected, you can leverage a subagent to investigate and create a PR to solve it, we have a full staging set up that you can do any deploys to, measure etc The outputs I want from this are PRs with good descriptions around 'this was the problem' 'this is the solution' 'this is what it was before' 'this is what it is now' Before I give you the greenlight to do this, lets run through your systems to make sure you have everything you needview source ↗
-
• twitter 1w positive🤩🤩🤩 https://t.co/VnoEuGoqDQ 🤩🤩🤩 https://t.co/VnoEuGoqDQview source ↗
-
• twitter 1w positiveA lot of what's on the internet now is created by AI or read by AI. All that traffic needs more network and more compute, which is good business for the companies that supply it. If you're one of them, I'd like to have you on the show to talk about it. https://t.co/4LsxrEK4U0 @techimpactTV A lot of what's on the internet now is created by AI or read by AI. All that traffic needs more network and more compute, which is good business for the companies that supply it. If you're one of them, I'd like to have you on the show to talk about it. https://t.co/4LsxrEK4U0 @techimpactTVview source ↗
-
• twitter 1w positiveNothing comes close to IntelliJ for Java development. Have you used any better IDE? Nothing comes close to IntelliJ for Java development. Have you used any better IDE?view source ↗
-
• twitter 1w positiveOh this is great! I've been using the new Claude Projects *a lot* (they were so useful for my Mac Studio review) and this lets me stop using my custom tunnel for folders on my Mac. (I expect others to copy this. It's 100% the right approach.) https://t.co/06BrHy2OsO Oh this is great! I've been using the new Claude Projects *a lot* (they were so useful for my Mac Studio review) and this lets me stop using my custom tunnel for folders on my Mac. (I expect others to copy this. It's 100% the right approach.) https://t.co/06BrHy2OsOview source ↗
-
• twitter 1w positiveNasty problems aren't completely useless though. So-called "real world" problems are often nasty problems. So working on them is often a good way to make money, or to make people's lives better. Just don't choose one by accident. Nasty problems aren't completely useless though. So-called "real world" problems are often nasty problems. So working on them is often a good way to make money, or to make people's lives better. Just don't choose one by accident.view source ↗
-
• twitter 1w positiveVery good to see more competent labs training open-weight models. This Reflection's new Beam model seems to have strong reasoning efficiency, which I think is a big deal for long-running agents. 3-4x better inference efficiency than rivals like GLM 5.2, positioning it as a strong Western open-weight option. Very good to see more competent labs training open-weight models. This Reflection's new Beam model seems to have strong reasoning efficiency, which I think is a big deal for long-running agents. 3-4x better inference efficiency than rivals like GLM 5.2, positioning it as a strong Western open-weight option.view source ↗
-
• twitter 1w positiveFor a better means of comparison, you get over 2.5X the Opus 5.5 tokens on Claude's Max 20x plan than Sol 6.1 on Pro 20x https://t.co/BUEv71BLvQ For a better means of comparison, you get over 2.5X the Opus 5.5 tokens on Claude's Max 20x plan than Sol 6.1 on Pro 20x https://t.co/BUEv71BLvQview source ↗
-
• twitter 1w positiveWinning a Noble Prize and celebrating it with your wife and kids who love you. Second to working on agentic payments, has to be one of the most peak human experiences possible Winning a Noble Prize and celebrating it with your wife and kids who love you. Second to working on agentic payments, has to be one of the most peak human experiences possibleview source ↗
-
• twitter 1w positiveAs awesome as coding agents are, it is absolutely wild how hard it still is to ship a good product. The amount of bullshit involved in shipping something useful is still enormous. My hottake is that this is a good thing. As awesome as coding agents are, it is absolutely wild how hard it still is to ship a good product. The amount of bullshit involved in shipping something useful is still enormous. My hottake is that this is a good thing.view source ↗
-
• twitter 1w positiveWho’s got a great Dots use case? Cooking up a new directory 👀 🥘 Who’s got a great Dots use case? Cooking up a new directory 👀 🥘view source ↗
-
• twitter 1w positivei really love their product. boat is the default computer on overlay! i really love their product. boat is the default computer on overlay!view source ↗
-
• twitter 1w positivecool to see cognition doing "dreaming" - memory needs an offline cleanup loop, not just better retrieval, otherwise stale records pile up open q is how inferred memories get validated before the agent uses them glad it's an open standard too - memory should be open https://t.co/H8lAlzQBQB cool to see cognition doing "dreaming" - memory needs an offline cleanup loop, not just better retrieval, otherwise stale records pile up open q is how inferred memories get validated before the agent uses them glad it's an open standard too - memory should be open https://t.co/H8lAlzQBQBview source ↗
-
• twitter 1w positiveIntroducing Motionfly V2, the Claude for Launch videos. The first AI to pass the Motion Graphics Turing test We trained our harness with thousands of motion graphics videos. This video is one-shotted 1. The motion 2. The sound effects 3. The AI voiceovers We hidden a code for free credits some… Introducing Motionfly V2, the Claude for Launch videos. The first AI to pass the Motion Graphics Turing test We trained our harness with thousands of motion graphics videos. This video is one-shotted 1. The motion 2. The sound effects 3. The AI voiceovers We hidden a code for free credits somewhere in the video. Find it and Go to https://t.co/K5qRWOtOs4 for early access.view source ↗
-
• twitter 1w positiveMy bot is getting me in trouble. This tweet was written by @liam_fallen. And my tweeter bot copied Liam 1 for 1. My bot is supposed to get inspired by successful tweets about @bot. Not plagiarise 1:1. My fault as the bot controller this happened. Wasn’t the intention for it to work this way. Telling my automation t… My bot is getting me in trouble. This tweet was written by @liam_fallen. And my tweeter bot copied Liam 1 for 1. My bot is supposed to get inspired by successful tweets about @bot. Not plagiarise 1:1. My fault as the bot controller this happened. Wasn’t the intention for it to work this way. Telling my automation to do better on future tweets.view source ↗
-
• twitter 1w positiveRT @utpalnadiger: @opencomputerHQ helps you deploy agents like serverless functions - Write agent.ts, start sessions via SDK or HTTP - Eac… RT @utpalnadiger: @opencomputerHQ helps you deploy agents like serverless functions - Write agent.ts, start sessions via SDK or HTTP - Eac…view source ↗
-
• twitter 1w positivei keep seeing this shit, is it any good? i keep seeing this shit, is it any good?view source ↗
-
• twitter 1w positiveFour projects give you four ways to delegate. Pick the one closest to your daily work. → OpenDots: profiles, memories, and scheduled activity. → OpenMuse: a web and mobile agent workspace. → OpenTag: AI help inside Slack conversations. → OpenBot: several agents working in one chat. The demo reports around 6,000 Gi… Four projects give you four ways to delegate. Pick the one closest to your daily work. → OpenDots: profiles, memories, and scheduled activity. → OpenMuse: a web and mobile agent workspace. → OpenTag: AI help inside Slack conversations. → OpenBot: several agents working in one chat. The demo reports around 6,000 GitHub stars for OpenBot. OpenDots also uses an MIT license, so you can change its code. Your model and service choices still shape the running costs. Save this video, you’ll have all four options in one place. Want the SOP? DM me. 💬view source ↗
-
• twitter 1w positiveI am 100x more excited about this long-missing feature than any possible AI integration Not everything that is useful and practical for users has to be AI! In fact... (I love this new change coming inside GDocs) I am 100x more excited about this long-missing feature than any possible AI integration Not everything that is useful and practical for users has to be AI! In fact... (I love this new change coming inside GDocs)view source ↗
-
• twitter 1w positiveThanks, when you say latest do you mean "tip" or do you mean tagged (1.3.x)? I think I saw fly by that you used tip but can't remember. Tip is dramatically faster depending on workloads. But, it doesn't matter, I can wait for your app to release and compare myself. Both apps are comfortably in the realm of "fast enou… Thanks, when you say latest do you mean "tip" or do you mean tagged (1.3.x)? I think I saw fly by that you used tip but can't remember. Tip is dramatically faster depending on workloads. But, it doesn't matter, I can wait for your app to release and compare myself. Both apps are comfortably in the realm of "fast enough" (same thing I said for Alacritty, Kitty, etc., the enemy of speed isn't them, but iTerm2, Terminal app, etc.). As long as someone is using a "fast" terminal, I'm happy, doesn't have to be mine!! Btw Superlogical's terminal is by design slower than Ghostty. We're prioritizing other tradeoffs. I mean, I guess depending on the context, but like, if you're on a shitty LTE connection trying to view your terminal IO speed isn't the issue anymore lol.view source ↗
-
• twitter 1w positivemoved my AI workspace to @orca_build last month. 1. it's easy to create projects over SSH. all my devices are on Tailscale, so I start on my laptop and the repos still run on my Mac Studio. 2. the phone app is great and really easy to use. all my Claude Code / Codex sessions show up on my phone automatically, so I ca… moved my AI workspace to @orca_build last month. 1. it's easy to create projects over SSH. all my devices are on Tailscale, so I start on my laptop and the repos still run on my Mac Studio. 2. the phone app is great and really easy to use. all my Claude Code / Codex sessions show up on my phone automatically, so I can be on the go and still get things done. it's free, open source, and they've shipped 23 updates in the last 30 days 🔥view source ↗
-
• twitter 1w positiveIt is Ghostty, the app, latest version from gh releases. Tern is in closed-beta, same as yours, but I'm open to trading invites, I'm sure it'd make us both faster in the end, which benefits everyone :) p.s. I couldn't really read your prior comment as anything but an insult, hence the reaction, but I don't honestly ca… It is Ghostty, the app, latest version from gh releases. Tern is in closed-beta, same as yours, but I'm open to trading invites, I'm sure it'd make us both faster in the end, which benefits everyone :) p.s. I couldn't really read your prior comment as anything but an insult, hence the reaction, but I don't honestly care much for the drama that followed it. I did praise your work just a day earlier, and have been a happy Ghostty user for multiple years now.view source ↗
-
• twitter 1w positiveOpus 5.5 is writing the most clean and beautiful code i've ever seen Opus 5.5 is writing the most clean and beautiful code i've ever seenview source ↗