•twitter7957
listening to
timeline
7957
mentions
tracked
tracked
net sentiment
+25%
2583 positive
4771 neutral
603 negative
volume & sentiment over time
Sep 30 – Oct 6, 2026 · Daily
sources
most discussed
—
active days
7
mentions
Showing 7826–7850 of 7957 mentions
-
• twitter 5d neutralI built a claude skill that automates cartoon ads. everything is done, in just one prompt. > scriptwriting > scene generation > voice overs > competitor analysis -> everything under 5 min. this is maybe gonna change the hole ecom haha. follow for more ecom tutorials Comment "WANT" for Tutorial and Too… I built a claude skill that automates cartoon ads. everything is done, in just one prompt. > scriptwriting > scene generation > voice overs > competitor analysis -> everything under 5 min. this is maybe gonna change the hole ecom haha. follow for more ecom tutorials Comment "WANT" for Tutorial and Toolview source ↗
-
• twitter 5d neutrali’m seriously thinking about starting this challenge: clone a $5M/month mobile game and make $1,000 in less than 1 month too hard? easy? impossible? https://t.co/9Qi199mC02 i’m seriously thinking about starting this challenge: clone a $5M/month mobile game and make $1,000 in less than 1 month too hard? easy? impossible? https://t.co/9Qi199mC02view source ↗
-
• twitter 5d positiveA good example @johnonolan sent me today An Apple Store in Dubai where you have Apple Watches lying around freely with the door open, not secured, not behind glass Right by the front door! A high trust society like we used to have too https://t.co/rCAOwg9Kch A good example @johnonolan sent me today An Apple Store in Dubai where you have Apple Watches lying around freely with the door open, not secured, not behind glass Right by the front door! A high trust society like we used to have too https://t.co/rCAOwg9Kchview source ↗
-
• twitter 5d neutralFluffy character animations https://t.co/owojr1pMaC https://t.co/8tIgj05Ojq Fluffy character animations https://t.co/owojr1pMaC https://t.co/8tIgj05Ojqview source ↗
-
• twitter 5d neutralThis had me questioning phone calculators, @grok why are the results different on iPhone and android and which one is correct ? https://t.co/k4L5MpnPGu This had me questioning phone calculators, @grok why are the results different on iPhone and android and which one is correct ? https://t.co/k4L5MpnPGuview source ↗
-
• twitter 5d positiveI've angel invested in 3 startups shared in the Cursor angel group so far Reach out if you're working on something new, love to share with the group (60+ angels) I've angel invested in 3 startups shared in the Cursor angel group so far Reach out if you're working on something new, love to share with the group (60+ angels)view source ↗
-
• twitter 5d neutralOpus 5.5 ile hem çizdirdim, hem hareketlendirdim, hem de projeye entegre ettim. Tamamı Json... https://t.co/slVOwdeeiy Opus 5.5 ile hem çizdirdim, hem hareketlendirdim, hem de projeye entegre ettim. Tamamı Json... https://t.co/slVOwdeeiyview source ↗
-
• twitter 5d neutralNew paper release from @lossfunk We find that something as simple as saying information is from a "verified source" flips the answer of an LLM. It has implications on how the LLM answers if information it fetches online simply asserts it is a verified source. New paper release from @lossfunk We find that something as simple as saying information is from a "verified source" flips the answer of an LLM. It has implications on how the LLM answers if information it fetches online simply asserts it is a verified source.view source ↗
-
• twitter 5d positiveThe best TUI library out there https://t.co/WLvs7oFP6L The best TUI library out there https://t.co/WLvs7oFP6Lview source ↗
-
• twitter 5d neutralThis design is on another level of cleanliness. https://t.co/JveaJDw5eL This design is on another level of cleanliness. https://t.co/JveaJDw5eLview source ↗
-
• twitter 5d neutralthe next step in context engineering is knowledge system engineering we shouldnt just give agents context. we should build a typed knowledge base, agent capabilities and apps / views we use together then packaging that system so others can use it with their own data the next step in context engineering is knowledge system engineering we shouldnt just give agents context. we should build a typed knowledge base, agent capabilities and apps / views we use together then packaging that system so others can use it with their own dataview source ↗
-
• twitter 5d neutralHoly shit https://t.co/gHepyT0wIc Holy shit https://t.co/gHepyT0wIcview source ↗
-
• twitter 5d neutralLooking for more tech people on my timeline. If you're into tech, let’s connect 🤝 Looking for more tech people on my timeline. If you're into tech, let’s connect 🤝view source ↗
-
• twitter 5d neutralone-shot by sonnet 5.5 https://t.co/BbHeg5Rfhv one-shot by sonnet 5.5 https://t.co/BbHeg5Rfhvview source ↗
-
• twitter 5d neutralJust passed 12,000 stars across my GitHub repos! Up from a few hundred in early 2025. You can just do things! https://t.co/aBh3UMnMLo https://t.co/jeFBcHsweZ https://t.co/pRLV8a43IP Just passed 12,000 stars across my GitHub repos! Up from a few hundred in early 2025. You can just do things! https://t.co/aBh3UMnMLo https://t.co/jeFBcHsweZ https://t.co/pRLV8a43IPview source ↗
-
• twitter 5d positivesome daily papers i really liked last month ↓ https://t.co/LplZJylC22 some daily papers i really liked last month ↓ https://t.co/LplZJylC22view source ↗
-
• twitter 5d positiveCooked Another Launch Video For @geteigen 🔥🥶 https://t.co/30ZQWZKiYr Cooked Another Launch Video For @geteigen 🔥🥶 https://t.co/30ZQWZKiYrview source ↗
-
• twitter 5d positiveRelease 🚨 America dot gov is boring. I am happy to release 275k public Indian gov documents parsed from 15k gov websites. 322k official PDFs and on 128 topics, available to plug and play into any RAG frameowrk of your choice. Both raw data and cleaned data available in csv, parquet and SQLite format. At least 50k pages… Release 🚨 America dot gov is boring. I am happy to release 275k public Indian gov documents parsed from 15k gov websites. 322k official PDFs and on 128 topics, available to plug and play into any RAG frameowrk of your choice. Both raw data and cleaned data available in csv, parquet and SQLite format. At least 50k pages are useful. :D Will be updating this to 20 Million documents by month end (process running on JarvisLabs autonomously. Happy to share tracking link for those interested) Go build your Indian gov chatbot. No license, no credits needed. <3view source ↗
-
• twitter 5d positiveCan't believe https://t.co/x3xBr79cZP is free? https://t.co/JEkBOqNEzF Can't believe https://t.co/x3xBr79cZP is free? https://t.co/JEkBOqNEzFview source ↗
-
• twitter 5d neutralgpt 6.1 sol is quite pleasant to use https://t.co/4O5TKaMqWm gpt 6.1 sol is quite pleasant to use https://t.co/4O5TKaMqWmview source ↗
-
• twitter 5d positiveBuild 👏 more 👏 backlinks Build 👏 more 👏 backlinksview source ↗
-
• twitter 5d neutralPeople here on x post of making $10000 per months, all those faceless youtube channel earning millions. App making 2000$ month, some are making 8000$ per month by selling ebooks, are these people even real? Or all are engagement farmers ? Specially the tech guys People here on x post of making $10000 per months, all those faceless youtube channel earning millions. App making 2000$ month, some are making 8000$ per month by selling ebooks, are these people even real? Or all are engagement farmers ? Specially the tech guysview source ↗
-
• twitter 5d positiveThis week's episode on Subtext is with @ponnappa, founder of @realfastai. Many on X (and Bangalore tech) don't need an introduction to him. Those who do should know he's one of the smartest founders thinking about what an AI-native firm looks like. Full episode out tomorrow! https://t.co/CM05QKe6ly This week's episode on Subtext is with @ponnappa, founder of @realfastai. Many on X (and Bangalore tech) don't need an introduction to him. Those who do should know he's one of the smartest founders thinking about what an AI-native firm looks like. Full episode out tomorrow! https://t.co/CM05QKe6lyview source ↗
-
• twitter 5d negativeAs a Backend Engineer in the AI era, you must build these projects. 1.) High-Concurrency HTTP Server Build: Go or Rust server handling 10k+ concurrent connections with graceful shutdown and backpressure. Why: Concurrency architecture is the one thing AI cannot design for you. 2.) Multi-Tenant Hybrid Search Databas… As a Backend Engineer in the AI era, you must build these projects. 1.) High-Concurrency HTTP Server Build: Go or Rust server handling 10k+ concurrent connections with graceful shutdown and backpressure. Why: Concurrency architecture is the one thing AI cannot design for you. 2.) Multi-Tenant Hybrid Search Database Build: Postgres with Row-Level Security + pgvector + BM25 hybrid ranking across isolated tenants. Why: Structured data and semantic embeddings now share one query engine. 3.) Event-Sourced Order Pipeline Build: Kafka or NATS pipeline with immutable events, dead-letter queues, exactly-once semantics. Why: AI workloads are slow and async. The main thread must never block. 4.) Durable Onboarding Workflow Build: 3-day Temporal workflow with checkpoints, retries and human approval steps. Why: Background jobs are for emails. Durable execution is for multi-step agents. 5.) AI Gateway with Semantic Cache Build: Proxy that caches similar prompts via embeddings, enforces token budgets and fails over to a cheaper model on 503s. Why: The gateway protects your margins and your uptime from flaky, expensive LLM APIs. 6.) PII-Redacting Auth Middleware Build: OAuth2/OIDC provider plus middleware that masks PII before logging and restricts AI agents to read-only DB roles. Why: When agents can write to your database, a prompt injection is a data breach. 7.) Real-Time Streaming Dashboard Build: SSE/WebSocket dashboard streaming LLM tokens and database updates simultaneously with backpressure. Why: Time-To-First-Token and perceived latency are the new UX standards. 8.) Correlated Tracing Pipeline Build: OpenTelemetry + Langfuse pipeline linking each HTTP request to the exact LLM prompt and DB query it triggered. Why: You cannot debug a hallucination without replaying the exact context the model saw. 9.) Ephemeral Environment Provisioner Build: Terraform or Pulumi scripts spinning up a complete isolated staging environment for every pull requeview source ↗
-
• twitter 5d positiveGPT-6 Sol & Opus 5.5 + Unreal + Blender Enjoy the beauty 😊 https://t.co/0OhStTG6w5 GPT-6 Sol & Opus 5.5 + Unreal + Blender Enjoy the beauty 😊 https://t.co/0OhStTG6w5view source ↗