•twitter6064
listening to
timeline
6064
mentions
tracked
tracked
net sentiment
+24%
1929 positive
3673 neutral
462 negative
volume & sentiment over time
Sep 30 – Oct 5, 2026 · Daily
sources
most discussed
—
active days
6
mentions
Showing 1601–1625 of 6064 mentions
-
• twitter 1d neutral4 Leadership Lessons From Marcus Aurelius https://t.co/4eZvmXlhaL 4 Leadership Lessons From Marcus Aurelius https://t.co/4eZvmXlhaLview source ↗
-
• twitter 1d negativeAndrej Karpathy tip for Claude Code: once Opus 5.5 writes your code, stop asking Opus to review its own blind spots and stop burning local context on PR checks hand verification to an adversarial cloud fleet with /code-review ultra run /code-review ultra --post Opus 5.5 plans architecture and writes the core logic S… Andrej Karpathy tip for Claude Code: once Opus 5.5 writes your code, stop asking Opus to review its own blind spots and stop burning local context on PR checks hand verification to an adversarial cloud fleet with /code-review ultra run /code-review ultra --post Opus 5.5 plans architecture and writes the core logic Sonnet 5.5 swarms local refactors and tests at medium effort The Cloud Reviewer Fleet launches in an isolated sandbox, spins up adversarial verifiers, and only reports bugs at three proven gates: → before opening a PR: does this diff break cross-module invariants? → reproduction check: can an independent verifier write a failing test proving the bug? → pre-merge signoff: zero style nits, every reported finding reproduced in bugs.json Sonnet 5.5 builds. Opus 5.5 ships. Cloud fleet breaks and verifies Jev engineering is the same move one layer down: mechanical decisions that need no reasoning (diff size calculation, git base detection, AST tree filtering, skip style nits) resolve in under 16ms, so the frontier models only wake up when logic actually branches Code on high. Swarm on medium. Verify with ultrareview. - the full verification tree > Opus 5.5 on high runs the local development session > worker edits and runs local test suites > explorer reads repo context and maps dependencies > all local subagents on Sonnet 5.5 at medium effort > /code-review ultra spins up an adversarial cloud fleet on Anthropic infrastructure > independent verifiers write tests to prove each bug before reporting > bugs.json automatically stamps verified PR comments via --post paste the tree and this prompt into Claude Code ↓ "Configure my Claude Code workspace for cloud fleet verification: 1. Audit ~/.claude/agents and .claude/agents for subagents fitting worker and explorer: > Give each model: sonnet, effort: medium > Keep all local exploration out of main context 2. Lock main session effortLevel to high in ~/.claude/settings.json 3. Configure ultrareview defaultsview source ↗
-
• twitter 1d neutralWhen doing well becomes a demand to be flawless, the pressure can interfere with the qualities that help careers grow: creativity, flexibility, collaboration and the willingness to learn. Read more: https://t.co/Y0zZENrokV https://t.co/Ag7gvez3dH When doing well becomes a demand to be flawless, the pressure can interfere with the qualities that help careers grow: creativity, flexibility, collaboration and the willingness to learn. Read more: https://t.co/Y0zZENrokV https://t.co/Ag7gvez3dHview source ↗
-
• twitter 1d neutralThe @OpenAI Dots are literally getting dumber every day; they can't properly manage multiple hosts, they request permissions for every single step they take (and they're on "Full access"). As always, Hermes is unbeatable @NousResearch The @OpenAI Dots are literally getting dumber every day; they can't properly manage multiple hosts, they request permissions for every single step they take (and they're on "Full access"). As always, Hermes is unbeatable @NousResearchview source ↗
-
• twitter 1d neutralhttps://t.co/xNequCy3kN https://t.co/xNequCy3kNview source ↗
-
• twitter 1d neutralMicrosoft is backing an effort with Snowflake and others to standardize business metrics so AI tools can more easily understand company data. The move marks an about-face from Microsoft’s earlier effort to protect Fabric from rivals. Full story: https://t.co/rXk7tt2WCK Microsoft is backing an effort with Snowflake and others to standardize business metrics so AI tools can more easily understand company data. The move marks an about-face from Microsoft’s earlier effort to protect Fabric from rivals. Full story: https://t.co/rXk7tt2WCKview source ↗
-
• twitter 1d neutralWhat do you usually give Hermes so it knows a task is actually done? A test, expected output, checklist, something else? What do you usually give Hermes so it knows a task is actually done? A test, expected output, checklist, something else?view source ↗
-
• twitter 1d positiveNEW LOVE TRIANGLE UNLOCKED https://t.co/7j7okBySmX NEW LOVE TRIANGLE UNLOCKED https://t.co/7j7okBySmXview source ↗
-
• twitter 1d neutralThis guy Lino who built a $60K/month app in 6 months with zero coding experience says: you just need to learn from people in the app space and ship... "He'd never even written a single line of code. But he just started learning from people in the app space, shipped his first app, and today, that app that he built is a… This guy Lino who built a $60K/month app in 6 months with zero coding experience says: you just need to learn from people in the app space and ship... "He'd never even written a single line of code. But he just started learning from people in the app space, shipped his first app, and today, that app that he built is about to hit $60K a month." "I launched my first app, AbMaxx, about 5 months ago, and now we're on pace to hit $60K this month." "I was able to scale these kind of numbers in such a short amount of time with literally zero coding experience and absolutely not technical at all."view source ↗
-
• twitter 1d positiveGood humor will always be politically incorrect. https://t.co/T8Dv9c4PGI Good humor will always be politically incorrect. https://t.co/T8Dv9c4PGIview source ↗
-
• twitter 1d neutralWe need an RSI meta-learning scaling law to disambiguate things once and for all. The reality is the archtiecture improvements still depends heavily on test-time compute scaling of synthetic researchers, so basically counts as compute scaling for the architecture search We need an RSI meta-learning scaling law to disambiguate things once and for all. The reality is the archtiecture improvements still depends heavily on test-time compute scaling of synthetic researchers, so basically counts as compute scaling for the architecture searchview source ↗
-
• twitter 1d neutralwe now know what the second button does. it ships features. the first one is furious https://t.co/nk34tGKw4o we now know what the second button does. it ships features. the first one is furious https://t.co/nk34tGKw4oview source ↗
-
• twitter 1d positiveLove this app https://t.co/J3l8uSXdnv https://t.co/zHk1jDOqpW Love this app https://t.co/J3l8uSXdnv https://t.co/zHk1jDOqpWview source ↗
-
• twitter 1d positiveسنوافيكم في حال تم #تعليق_الدراسة بالمناطق التي تشهد امطار غزيرة ⛈️ ❤️ لايك ❤️ سنوافيكم في حال تم #تعليق_الدراسة بالمناطق التي تشهد امطار غزيرة ⛈️ ❤️ لايك ❤️view source ↗
-
• twitter 1d positivegrok bot is by far the best out of all these. grok bot is by far the best out of all these.view source ↗
-
• twitter 1d neutralVery proud of the impact of all our work using AI to accelerate science and medicine for the benefit of society. Very proud of the impact of all our work using AI to accelerate science and medicine for the benefit of society.view source ↗
-
• twitter 1d positive😂 @andy_murray 😘 Thank you for being part of such special days at the @rnadalacademy. I really enjoyed seeing us back on court together… even if it didn’t look like it 😂 https://t.co/wO47CJ9V0K 😂 @andy_murray 😘 Thank you for being part of such special days at the @rnadalacademy. I really enjoyed seeing us back on court together… even if it didn’t look like it 😂 https://t.co/wO47CJ9V0Kview source ↗
-
• twitter 1d neutralI used Claude Code and Cursor to answer the exact same question: was Opus 5.5 nerfed? and it got more interesting than I expected! ofc I used same model, same frozen repo, same prompt. and same reasoning level Claude Code: 8/9 Cursor: 9/9 So the experiment ended up showing me something bigger than just “nerfed or not”:… I used Claude Code and Cursor to answer the exact same question: was Opus 5.5 nerfed? and it got more interesting than I expected! ofc I used same model, same frozen repo, same prompt. and same reasoning level Claude Code: 8/9 Cursor: 9/9 So the experiment ended up showing me something bigger than just “nerfed or not”: The harness matters A LOT Same model doesn’t necessarily mean the same agent behavior My takeaway: when evaluating coding agents, benchmark the model + harness combination you actually use, not the model name in isolationview source ↗
-
• twitter 1d positivewhat 7 days of consistent work can do: - over 500 new followers. - approx. 35K impressions - 1.4K engagements - 300+ profile visits. - countless amount of fun + learning it’s not much but its a great start and i am super happy to have achieved this. fully intending to double down on this. for anyone trying and not … what 7 days of consistent work can do: - over 500 new followers. - approx. 35K impressions - 1.4K engagements - 300+ profile visits. - countless amount of fun + learning it’s not much but its a great start and i am super happy to have achieved this. fully intending to double down on this. for anyone trying and not seeing much results, don’t worry and don’t you ever think of stopping. just keep pushing and keep doing your best. we are in this together. let’s grow together and achieve our dreams 🙌view source ↗
-
• twitter 1d neutralFolks if you haven’t already, you have 5 days to setup a Hermes agent on a VPS that runs outreach and marketing for you 24/7. It’s time. Folks if you haven’t already, you have 5 days to setup a Hermes agent on a VPS that runs outreach and marketing for you 24/7. It’s time.view source ↗
-
• twitter 1d neutralsuggest open source repos to contribute , pref python codebase suggest open source repos to contribute , pref python codebaseview source ↗
-
• twitter 1d neutralthe more i use claude artifacts, the more i see why figma is paranoid about anthropic the more i use claude artifacts, the more i see why figma is paranoid about anthropicview source ↗
-
• twitter 1d neutralCan we hit 3.2k today?? https://t.co/iqGOHyFxOL Can we hit 3.2k today?? https://t.co/iqGOHyFxOLview source ↗
-
• twitter 1d neutralI beat Seedance 2.5 on cost and quality. The first 15s video cost me $0.40 The Seedance 2.5 cost me $4.73 You can see them side by side here: https://t.co/3OpmzUv6g2 I beat Seedance 2.5 on cost and quality. The first 15s video cost me $0.40 The Seedance 2.5 cost me $4.73 You can see them side by side here: https://t.co/3OpmzUv6g2view source ↗
-
• twitter 1d neutralPretty much. Manchester City just dared England. And they have receipts. Receipts with Andy Burnham and PGMOL. Pretty much. Manchester City just dared England. And they have receipts. Receipts with Andy Burnham and PGMOL.view source ↗