•twitter17678
listening to
timeline
17678
mentions
tracked
tracked
net sentiment
+24%
5505 positive
10864 neutral
1309 negative
volume & sentiment over time
Sep 30 – Oct 16, 2026 · Daily
sources
most discussed
—
active days
17
mentions
Showing 12176–12200 of 17678 mentions
-
• twitter 1w positivelooking for a video editor asap 15 × 30-second videos, fully edited—captions, screen recordings, clean cuts + sound design. budget: ₹15k turnaround: under 24 hours dm me your portfolio + availability. please only reach out if you can hit the deadline. RTs appreciated 🙏 looking for a video editor asap 15 × 30-second videos, fully edited—captions, screen recordings, clean cuts + sound design. budget: ₹15k turnaround: under 24 hours dm me your portfolio + availability. please only reach out if you can hit the deadline. RTs appreciated 🙏view source ↗
-
• twitter 1w negative“We believe the world should accept some bad things happening for the benefits of this technology.” (…) “And it’s so powerful and so dangerous…” I get the feeling that, contrary to Trumps push for acceleration, there are continued attempts to bring about a slowdown by repeatedly emphasizing concerns. Yet both are… “We believe the world should accept some bad things happening for the benefits of this technology.” (…) “And it’s so powerful and so dangerous…” I get the feeling that, contrary to Trumps push for acceleration, there are continued attempts to bring about a slowdown by repeatedly emphasizing concerns. Yet both are possible at the same time: acceleration and safety. The greater danger lies in slowing down if you’d ask me, as doing so negligently hinders the rapid discovery of solutions for diseases, hunger, and more. https://t.co/r0rTLgslpEview source ↗
-
• twitter 1w neutralRT @XFreeze: Tesla just took the top two spots in the entire Netherlands new-car market 🇳🇱 Not just EVs...every car September registratio… RT @XFreeze: Tesla just took the top two spots in the entire Netherlands new-car market 🇳🇱 Not just EVs...every car September registratio…view source ↗
-
• twitter 1w neutralFABLE 5.5 IS SO MUCH CHEAPER HOLY SHIT they basically cut token waste by 30%!!! in my unscientific design test... - Fable 5 Max: $81.74 - Fable 5.1 Max: $79.04 - Fable 5.5 Max: $57.16* - Fable 5 High: $31.23 - Fable 5.1 High: $25.98 - Fable 5.5 High: $18.39* - Fable 5 Low: $13.78 - Fable 5.1 Low: $16.46 - Fable 5… FABLE 5.5 IS SO MUCH CHEAPER HOLY SHIT they basically cut token waste by 30%!!! in my unscientific design test... - Fable 5 Max: $81.74 - Fable 5.1 Max: $79.04 - Fable 5.5 Max: $57.16* - Fable 5 High: $31.23 - Fable 5.1 High: $25.98 - Fable 5.5 High: $18.39* - Fable 5 Low: $13.78 - Fable 5.1 Low: $16.46 - Fable 5.5 Low: $16.07* * assumes Fable 5.1 pricing from 5.1 to 5.5 this means: - about -28% on Max - about 29% on High - only 2% on Low cost wise, Fable 5.1 Low now buys Fable 5.5 High what the fuck? HUGE!!!view source ↗
-
• twitter 1w positiveThis is f*cking incredible. This Claude Code command fired me from babysitting Opus 5.5 once Opus 5.5 runs your long tasks, stop burning your nights typing "continue", while Haiku sits idle hand the finish line to a judge that isn't Opus and let it run all night run /goal npm test exits 0 and git status is clean, or… This is f*cking incredible. This Claude Code command fired me from babysitting Opus 5.5 once Opus 5.5 runs your long tasks, stop burning your nights typing "continue", while Haiku sits idle hand the finish line to a judge that isn't Opus and let it run all night run /goal npm test exits 0 and git status is clean, or stop after 20 turns Opus 5.5 writes the code and runs the tests, turn after turn Auto mode approves its tool calls inside each turn Haiku reads the transcript after every turn, never touches a file, and only answers in three ways: → not yet met: Opus takes the reason as its next order and keeps going → met: goal clears and logs an achieved entry → impossible: goal clears with the reason instead of burning tokens till sunrise Opus 5.5 works. Haiku judges. You sleep Jev engineering is the same move one layer down: yes/no calls inside the loop (same error as last turn, did the diff leave scope, retry or stop) go to Jev in ~100 ms, and the big model only thinks where thinking pays anyone still typing "continue" at 2am isn't running an agent, they're its while loop The full tree > Opus 5.5 on high runs the main session > Auto mode approves tool calls inside each turn > /goal holds one measurable end state and a stated check > "or stop after 20 turns" is the leash > Haiku judges after every turn > a prompt-based Stop hook in settings.json does the same for every session paste build and this prompt into Claude Code ↓ "Set up my Claude Code for unattended runs around this tree: 1. Read this repo and my recent sessions and draft three /goal conditions from my real work. > One measurable end state each: a test result, an exit code, an empty queue > A stated check, like "npm test exits 0" > What must not change on the way, plus "or stop after 20 turns" 2. Check ~/.claude/settings.json and .claude/settings.json for disableAllHooks or allowManagedHooksOnly, which switch /goal off 3. Check whether CLAUDE_CODE_GOAL_CHECKIN_MINUTES or ANTHROPIC_DEFAULT_Hview source ↗
-
• twitter 1w positiveI made my first $1 online today. ❤️ It’s just $1. But someone believed in what I built enough to pay for it. First dollar: done✅️. Next goal: $10K. 🚀 Let’s see how far I can take this. https://t.co/Sx9dEKS82L I made my first $1 online today. ❤️ It’s just $1. But someone believed in what I built enough to pay for it. First dollar: done✅️. Next goal: $10K. 🚀 Let’s see how far I can take this. https://t.co/Sx9dEKS82Lview source ↗
-
• twitter 1w neutralThis McDonald's employee has finally retired after 32 years of service 🫡 https://t.co/q9R0ei7jjW This McDonald's employee has finally retired after 32 years of service 🫡 https://t.co/q9R0ei7jjWview source ↗
-
• twitter 1w neutralhttps://t.co/ayw2vz7DC1 https://t.co/ayw2vz7DC1view source ↗
-
• twitter 1w neutralSpanish Prime Minister Pedro Sanchez called fresh elections for next month after protests against high housing costs https://t.co/MqpT96dPgW Spanish Prime Minister Pedro Sanchez called fresh elections for next month after protests against high housing costs https://t.co/MqpT96dPgWview source ↗
-
• twitter 1w neutralHere we go with a demo video for @getBluma (YC F25) https://t.co/oNKVCUNSzM Here we go with a demo video for @getBluma (YC F25) https://t.co/oNKVCUNSzMview source ↗
-
• twitter 1w positiveIf you have Google Docs, Claude and 1 hour every day... You can earn $8,400 per month. Comment “DOC” and I’ll send you a FREE training breaking the entire system down. (With all the AI prompts) ⏳ Taking this down in 24 hours https://t.co/22YKIBenC1 If you have Google Docs, Claude and 1 hour every day... You can earn $8,400 per month. Comment “DOC” and I’ll send you a FREE training breaking the entire system down. (With all the AI prompts) ⏳ Taking this down in 24 hours https://t.co/22YKIBenC1view source ↗
-
• twitter 1w neutralSTAY POSITIVE!!! STAY POSITIVE!!!view source ↗
-
• twitter 1w neutralStealth Venture just joined TrustMRR 💰 Revenue (30d): $17k 💵 Total revenue: $104k 📈 Growth (30d): +34% 💸 Profit margin: 20% https://t.co/kh8Khc00YI Stealth Venture just joined TrustMRR 💰 Revenue (30d): $17k 💵 Total revenue: $104k 📈 Growth (30d): +34% 💸 Profit margin: 20% https://t.co/kh8Khc00YIview source ↗
-
• twitter 1w positiveOpus 5.5 is fixing my imposter syndrome. The last couple generations of models did 2 things: - caused orgs to prioritise shipping speed so much that engineers everywhere had large knowledge gaps about the code their models were shipping. Poor reviews, poor mental models, and essentially this state of constant anxiety… Opus 5.5 is fixing my imposter syndrome. The last couple generations of models did 2 things: - caused orgs to prioritise shipping speed so much that engineers everywhere had large knowledge gaps about the code their models were shipping. Poor reviews, poor mental models, and essentially this state of constant anxiety due to being out of touch with things they’re accountable for. - models had so much verbosity in their explanations that it wasn’t even possible to read whatever they were generating. It was impossible to ask an LLM about the code it was writing without confusing yourself even more. Opus 5.5 fixed the second issue by being absolutely beautiful in terms of generating explanations using animations, interactive artifacts and just… very simple, easy-to-understand language. Not to mention, the code it writes narrows that gap even more. On the other hand, orgs have slowly started to adopt better engineering practices after watching their software go through massive quality issues. This feels like such a win. You don’t have to write code, reviewing is a lot easier, and you’re also now very familiar with the code you’re shipping.view source ↗
-
• twitter 1w positiveI’ve been quietly building a desktop app for people who like Herdr but want a more beautiful, native workspace. It’s called Ubra. Coding agents, side by side. Less terminal chaos. More flow. It’s almost here. Get notified → https://t.co/Cwk38iuWrv #BuildInPublic https://t.co/e0rJRk6eg9 I’ve been quietly building a desktop app for people who like Herdr but want a more beautiful, native workspace. It’s called Ubra. Coding agents, side by side. Less terminal chaos. More flow. It’s almost here. Get notified → https://t.co/Cwk38iuWrv #BuildInPublic https://t.co/e0rJRk6eg9view source ↗
-
• twitter 1w neutralEXCLUSIVE: Cost pressures and deadlock force Honda to rework India strategy, sources say https://t.co/TrBl73Q5je https://t.co/TrBl73Q5je EXCLUSIVE: Cost pressures and deadlock force Honda to rework India strategy, sources say https://t.co/TrBl73Q5je https://t.co/TrBl73Q5jeview source ↗
-
• twitter 1w positiveyou can now go from zero to your first Jev build, for FULL FREE guides, run steps and the best Jev projects, all in one place: https://t.co/rmKtrtINwv > hands-on guides for Python and JS/TS, with copy-paste code > context picking and agent next steps with allow, review and fallback rules > how-to-run for hand-picked… you can now go from zero to your first Jev build, for FULL FREE guides, run steps and the best Jev projects, all in one place: https://t.co/rmKtrtINwv > hands-on guides for Python and JS/TS, with copy-paste code > context picking and agent next steps with allow, review and fallback rules > how-to-run for hand-picked projects: stack, keys, exact commands > save your favorites, no account, still there after a reload > sort by use case or evidence, every link re-checked daily all of it free. no signup, no paywall. more than 39 new projects, repos and guides landed with this v1.4 update, and the list keeps growingview source ↗
-
• twitter 1w positiveWhat would you do if you knew you could not fail? Answer below, now it’s your turn. https://t.co/tZqhJf4Y0u What would you do if you knew you could not fail? Answer below, now it’s your turn. https://t.co/tZqhJf4Y0uview source ↗
-
• twitter 1w neutralhttps://t.co/1jRcAwciSA Signed https://t.co/1jRcAwciSA Signedview source ↗
-
• twitter 1w positivea /retro skill that reads your past agent sessions and suggests repo fixes! Feels like the harness is starting to learn from its own runs. https://t.co/KTSM2rhzr8 a /retro skill that reads your past agent sessions and suggests repo fixes! Feels like the harness is starting to learn from its own runs. https://t.co/KTSM2rhzr8view source ↗
-
• twitter 1w neutralI’m sorry Lauren I’m sure the next model will be usable I’m sorry Lauren I’m sure the next model will be usableview source ↗
-
• twitter 1w negativeBairstow turned the cricket ground into a comedy show for a moment 😭😂 Even the cameraman couldn’t believe he just got pranked live on air 😭 https://t.co/iJShXz8sRC Bairstow turned the cricket ground into a comedy show for a moment 😭😂 Even the cameraman couldn’t believe he just got pranked live on air 😭 https://t.co/iJShXz8sRCview source ↗
-
• twitter 1w positiveA jet plunging 16,000 feet in 30 seconds would feel like a 'very, very vertical roller coaster,' said Alberto Paduanelli, who recreated the flydubai incident in a simulator. Unlike a roller coaster, however, passengers would not expect the drop https://t.co/G3zSvHpFkZ https://t.co/UeX5dqG4zm A jet plunging 16,000 feet in 30 seconds would feel like a 'very, very vertical roller coaster,' said Alberto Paduanelli, who recreated the flydubai incident in a simulator. Unlike a roller coaster, however, passengers would not expect the drop https://t.co/G3zSvHpFkZ https://t.co/UeX5dqG4zmview source ↗
-
• twitter 1w neutralGrok 4.7 Grok 4.7view source ↗
-
• twitter 1w positiveno shade but unbelievable that warp is now trying to build this (they should have built it atleast a quarter ago) despite being late to the bandwagon, they haven’t thought about so many things for ex playbooks (ai loves to leave breadcrumbs for other agents and this is a great way for humans and agents to collaborate)… no shade but unbelievable that warp is now trying to build this (they should have built it atleast a quarter ago) despite being late to the bandwagon, they haven’t thought about so many things for ex playbooks (ai loves to leave breadcrumbs for other agents and this is a great way for humans and agents to collaborate) - keep it simple, .md stored over GitHubview source ↗