•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 601–625 of 1145 mentions
-
• twitter 1w negativeNew @LiteLLM Lens update: datasets. If you're building agents with Lens, the loop is now: 1. Lens finds your failing traces 2. You add them to a dataset 3. You run evals on your agents https://t.co/GTeS4B0BIP New @LiteLLM Lens update: datasets. If you're building agents with Lens, the loop is now: 1. Lens finds your failing traces 2. You add them to a dataset 3. You run evals on your agents https://t.co/GTeS4B0BIPview source ↗
-
• twitter 1w negativeI’m hiring AI operators. Looking for people who know how to use AI tools extremely well and can turn rough ideas into finished work. 💰 $2,500/month Remote. Long-term. Reply below if interested. I’m hiring AI operators. Looking for people who know how to use AI tools extremely well and can turn rough ideas into finished work. 💰 $2,500/month Remote. Long-term. Reply below if interested.view source ↗
-
• twitter 1w negativethis is pure f*cking golddd how to build your first ai agent (end-to-end walkthrough) if i’d had this in my hands a year ago, i would’ve shipped my first agent in a day instead of losing two weeks to trial and error in the right hands, this changes the entire playing field: https://t.co/8sKiqy36SO this is pure f*cking golddd how to build your first ai agent (end-to-end walkthrough) if i’d had this in my hands a year ago, i would’ve shipped my first agent in a day instead of losing two weeks to trial and error in the right hands, this changes the entire playing field: https://t.co/8sKiqy36SOview source ↗
-
• twitter 1w negativePre-seed VC in India, a typical Sunday: 20-yo founder gets our ₹3Cr term sheet → "quick 10 min call?" I join. His mom's on speaker, checking if we're a scam. Diligence goes both ways I guess😅 Anyways - Aunty is now on board. 😎 Pre-seed VC in India, a typical Sunday: 20-yo founder gets our ₹3Cr term sheet → "quick 10 min call?" I join. His mom's on speaker, checking if we're a scam. Diligence goes both ways I guess😅 Anyways - Aunty is now on board. 😎view source ↗
-
• twitter 1w negativeBuilder Arc - Learning's sharing time (Day 2) I launched lafda dot fun on Oct 4 at 12:45 PM IST, and it's been roughly 43 hours. > 20.2k pageviews, > 7.1k sessions, > 6.1k unique visitors, > average session duration 2 min 40 sec, > 94% of traffic from India, 64% on mobile, > 120 sign-ups, > 11 Lafda submissions, > 0 … Builder Arc - Learning's sharing time (Day 2) I launched lafda dot fun on Oct 4 at 12:45 PM IST, and it's been roughly 43 hours. > 20.2k pageviews, > 7.1k sessions, > 6.1k unique visitors, > average session duration 2 min 40 sec, > 94% of traffic from India, 64% on mobile, > 120 sign-ups, > 11 Lafda submissions, > 0 premium users so far (excluding me, of course). Now let's talk about bugs and glitches. I shipped 8 PRs since the last post, and 4 of them were fixes. From logging and observability, I caught: > One backend error was 97% of all my errors. Signed-out readers on a post page hit an account endpoint, got "not signed in" 3,867 times, and some saw a "Sign in required" toast without clicking anything. Fixed. It dropped from 3,738 a day to 2. > Every backend error was logged twice. Now it's logged once. (i forgot to turn of STDIO it in prod) > Failed sign-ins left no trace in my logs. Now they do. > Hydration error on the post page for signed-in readers (the page rendered twice). Fixed. > I removed my auth rate limit. Behind Cloudflare, many users shared one IP bucket, so real users could get blocked. Instead moved rate limit to WAF. > Big pastes failed to save (over 400 edits at once). Fixed. Only 1 user hit it (me ofc) From user reporting: > None Also shipped: notifications for comments and upvotes, a better paywall, an About page, and writing guidelines & enabled web vitals. I will report back with the analytics, issues, and monetization details.view source ↗
-
• twitter 1w negativethis language app made 184M organic views from 14 accounts their format: - crying hook -> app demo - the ai tutor roasts her so the app is the villain and it feels funny - one girl ran it 20 times, her worst one still did 1.5M you can check their entire UGC operation here for free https://t.co/FfDDNRxARw this language app made 184M organic views from 14 accounts their format: - crying hook -> app demo - the ai tutor roasts her so the app is the villain and it feels funny - one girl ran it 20 times, her worst one still did 1.5M you can check their entire UGC operation here for free https://t.co/FfDDNRxARwview source ↗
-
• twitter 1w negativea friend is hiring for an app studio. needs an ai-first operator. ideally an intern to start, with scope to go full-time. - paid. remote. no fixed hours. - your own projects or another job? no issue. - iim/management preferred, not a must. DM's open. a friend is hiring for an app studio. needs an ai-first operator. ideally an intern to start, with scope to go full-time. - paid. remote. no fixed hours. - your own projects or another job? no issue. - iim/management preferred, not a must. DM's open.view source ↗
-
• twitter 1w negativeEvery few days during dots development I would reset my dot to go through onboarding again. Not just the first few screens, but the full experience of prompting my dot to get to know me. It's getting increasingly painful. Pour one out for my latest dot 🫗🫗🫗 Every few days during dots development I would reset my dot to go through onboarding again. Not just the first few screens, but the full experience of prompting my dot to get to know me. It's getting increasingly painful. Pour one out for my latest dot 🫗🫗🫗view source ↗
-
• twitter 1w negativecontent will become infinite through agents. every brand pumping something out the second their agent's done which will cause an algorithmic backlash to the pace of it all.. and we'll reset back to slow content, where more selective, deeply curated things get shared to show "taste" content will become infinite through agents. every brand pumping something out the second their agent's done which will cause an algorithmic backlash to the pace of it all.. and we'll reset back to slow content, where more selective, deeply curated things get shared to show "taste"view source ↗
-
• twitter 1w negativeTibo says GPT-6 Astra and GPT-6.1 Sol got ~50% faster. I tested it: 20 tok/s → 30 tok/s. The +50% is real. But Claude Opus runs around 80 tok/s and Sonnet around 100. Faster than last week, but still pretty slow. https://t.co/rJqOV2yOWB Tibo says GPT-6 Astra and GPT-6.1 Sol got ~50% faster. I tested it: 20 tok/s → 30 tok/s. The +50% is real. But Claude Opus runs around 80 tok/s and Sonnet around 100. Faster than last week, but still pretty slow. https://t.co/rJqOV2yOWBview source ↗
-
• twitter 1w negativeI think we need a system that lets bots borrow credibility from humans. We can then separate credible agents from just pure spam. kinda like how the pair w the dragon in the avatar movie. https://t.co/XFrzrpmoLd I think we need a system that lets bots borrow credibility from humans. We can then separate credible agents from just pure spam. kinda like how the pair w the dragon in the avatar movie. https://t.co/XFrzrpmoLdview source ↗
-
• twitter 1w negativeI’ve never had an app like this before Churn? What churn?! https://t.co/FCSkXLoGnK I’ve never had an app like this before Churn? What churn?! https://t.co/FCSkXLoGnKview source ↗
-
• twitter 1w negativeI have made the decision to downgrade my Codex further from $100 to $20. I find that code reviews done by GPT-6.1 Sol has been pretty much on par with Astra for the most part (sometimes each model would find issues the other doesn't find). It's gonna be interesting. I have made the decision to downgrade my Codex further from $100 to $20. I find that code reviews done by GPT-6.1 Sol has been pretty much on par with Astra for the most part (sometimes each model would find issues the other doesn't find). It's gonna be interesting.view source ↗
-
• twitter 1w negativePlease don't buy anything without talking to me lol this is my thing. You can do a genuinely world-class system for ~$12k right now (sounds better than the $100k+ systems I've heard). Sonos is straight trash garbage dumpster fire tier. The software used to be good but now it's just as sloppy as the hardware. I got a … Please don't buy anything without talking to me lol this is my thing. You can do a genuinely world-class system for ~$12k right now (sounds better than the $100k+ systems I've heard). Sonos is straight trash garbage dumpster fire tier. The software used to be good but now it's just as sloppy as the hardware. I got a very expensive Sonos setup for my office recently and I regret missing the return window. Most good DACs have "broadcast" features for Spotify Connect, Airplay etc, don't worry too much there unless you really want multi-room music sync stuffview source ↗
-
• twitter 1w negativeCybersecurity moves quickly, and knowing what changed can make a difference. Subscribe to Roadmap Cybersecurity Weekly for a regular look at the issues shaping security today and your career tomorrow. https://t.co/Hrdxu82Vff https://t.co/7Yf2IHFIi5 Cybersecurity moves quickly, and knowing what changed can make a difference. Subscribe to Roadmap Cybersecurity Weekly for a regular look at the issues shaping security today and your career tomorrow. https://t.co/Hrdxu82Vff https://t.co/7Yf2IHFIi5view source ↗
-
• twitter 1w negativeHermes merged 142 PRs on October 5 The ones worth knowing: • Desktop shows a progress chip before a subscription hits its usage wall, and rate-limited providers say why and until when in the model pickers • Desktop Settings gets a single Plugins pane that holds every plugin's settings pages • Plugin skills now appear… Hermes merged 142 PRs on October 5 The ones worth knowing: • Desktop shows a progress chip before a subscription hits its usage wall, and rate-limited providers say why and until when in the model pickers • Desktop Settings gets a single Plugins pane that holds every plugin's settings pages • Plugin skills now appear as /plugin:skill in the TUI, Desktop, and CLI slash menus • hermes chat -q no longer hangs on approval, memory, MCP, or vault prompts nobody is around to answer • hermes update no longer stalls on a 20 minute git repack, and installs stop re-downloading repo history • The gateway brings back a platform whose plugin failed to load at startup without a restart, and Telegram delivers messages held during a disconnect • Dashboard login is hardened: capped request bodies, bounded login values, and spoofed X-Forwarded-For headers ignored • Catalog memory providers like hindsight and mnemosyne stop failing on every start, and installing one actually activates it • Memory writes stop failing on hand-formatted files, and refused writes tell you exactly what to fix • Local dictation now works on Windows ARM64 Desktop • Opus 5.5 keeps thinking on, and Anthropic summarized thinking no longer gets promoted to the final answer • New plugin hooks for human input requests, post gateway admission, and knowing which cron run you are in Here is the full list: DESKTOP IMPROVEMENTS (28 PRs) • feat(desktop): a progress chip warns before a subscription hits its usage wall • feat(desktop): a rate-limited provider says why and until when in the model pickers • feat(desktop): Settings ▸ Plugins: one pane for every plugin's settings pages (WoW AddOns style) • Desktop shared-metrics strip retires on the focused profile instead of coming back forever • fix(desktop): count limited accounts in credential-pool pickers • fix(desktop): Review scope tabs no longer overlap in a narrow pane • fix(desktop): stop refusing sends from a window behind its chat • fix(desktop): scope sidebarview source ↗
-
• twitter 1w negativeif anybody has tried to launch an ai character and has failed this is probably what you're doing wrong: - make sure your account is warmed up, so many people just go raw dog a new account and get pissed when they get 0 views. - engage with all of these other ai avatar accounts so your content fits right in with them -… if anybody has tried to launch an ai character and has failed this is probably what you're doing wrong: - make sure your account is warmed up, so many people just go raw dog a new account and get pissed when they get 0 views. - engage with all of these other ai avatar accounts so your content fits right in with them - dont just swap in one viral video and expect it go viral, you have to think through why this post went viral. me as a d1 scroller, for every viral video i find, i check WHY it went viral. i look through the comments what certain thing was it that triggered people. you have to go that deep - expect the worst, you see everybody else going viral in 2 days and expect to go viral as well. it does NOT work that way. i can tell you this, most of the accounts doing good right now either tried this on a different account OR have multiple accounts running. thats all for now.view source ↗
-
• twitter 1w negative@thdxr Staying on vanilla setups lets you absorb model improvements directly, whereas custom scaffolding usually just preserves workarounds for problems that no longer exist. @thdxr Staying on vanilla setups lets you absorb model improvements directly, whereas custom scaffolding usually just preserves workarounds for problems that no longer exist.view source ↗
-
• twitter 1w negative@fiapp_pro 谢谢反馈！ Remote server是实验功能，现在有一些链接的问题，都有在github issue上记录 我们有一个新版本的remote server 2.0会在这周发布，期待到时候给你更好的体验！ @fiapp_pro 谢谢反馈！ Remote server是实验功能，现在有一些链接的问题，都有在github issue上记录 我们有一个新版本的remote server 2.0会在这周发布，期待到时候给你更好的体验！view source ↗
-
• twitter 1w negativea weird inversion with LLMs is the models improve faster than the tinkerers when i see people with custom workflows and setups they're all addressing problems that don't exist anymore the person naively using vanilla codex is more likely to be experiencing state of the art a weird inversion with LLMs is the models improve faster than the tinkerers when i see people with custom workflows and setups they're all addressing problems that don't exist anymore the person naively using vanilla codex is more likely to be experiencing state of the artview source ↗
-
• twitter 1w negativeAddiction is only bad if you get addicted to the wrong things. Addiction is only bad if you get addicted to the wrong things.view source ↗
-
• twitter 1w negativeI think the reality people have to contend with as they tinker and optimize their agent harness in fall 2026, is that a lot of the gains you might have found a year ago, are much harder to find with the latest models. The frontier lab harnesses are by no means perfect, but the models are trained to use them well, and … I think the reality people have to contend with as they tinker and optimize their agent harness in fall 2026, is that a lot of the gains you might have found a year ago, are much harder to find with the latest models. The frontier lab harnesses are by no means perfect, but the models are trained to use them well, and it’s hard to outperform that.view source ↗
-
• twitter 1w negativeSomeone explain this to me. They sell this local AI machine for $3500, which is less than the individual components. They also emphasize there’s no subscription. To make things even more confusing, it has only 24GB of VRAM but 64 GB of ordinary RAM. So unless they somehow have a model that streams weights, the models i… Someone explain this to me. They sell this local AI machine for $3500, which is less than the individual components. They also emphasize there’s no subscription. To make things even more confusing, it has only 24GB of VRAM but 64 GB of ordinary RAM. So unless they somehow have a model that streams weights, the models it can run will be pretty bad. And even if they stream, they still will lose money on each sale. And please, don’t ever let a fake audience at a fake keynote clapview source ↗
-
• twitter 1w negativeYou NEED to be using Meta Muse It's not only an incredible AI agent, but it's the best agent for automating your every day tasks I have basically every task I hate doing automated now In this video I go over 6 use cases for Muse that has changed my life: https://t.co/VG6PdUzgOj You NEED to be using Meta Muse It's not only an incredible AI agent, but it's the best agent for automating your every day tasks I have basically every task I hate doing automated now In this video I go over 6 use cases for Muse that has changed my life: https://t.co/VG6PdUzgOjview source ↗
-
• twitter 1w negativeguys i think i found the guy who broke github this time https://t.co/shaLOOKhUi guys i think i found the guy who broke github this time https://t.co/shaLOOKhUiview source ↗