•twitter2798
listening to
timeline
2798
mentions
tracked
tracked
net sentiment
+24%
882 positive
1717 neutral
199 negative
volume & sentiment over time
Sep 30 – Oct 4, 2026 · Daily
sources
most discussed
—
active days
5
mentions
Showing 2676–2700 of 2798 mentions
-
• twitter 2d 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 2d positiveThe best TUI library out there https://t.co/WLvs7oFP6L The best TUI library out there https://t.co/WLvs7oFP6Lview source ↗
-
• twitter 2d 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 2d 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 2d neutralHoly shit https://t.co/gHepyT0wIc Holy shit https://t.co/gHepyT0wIcview source ↗
-
• twitter 2d 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 2d neutralone-shot by sonnet 5.5 https://t.co/BbHeg5Rfhv one-shot by sonnet 5.5 https://t.co/BbHeg5Rfhvview source ↗
-
• twitter 2d 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 2d 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 2d positiveCooked Another Launch Video For @geteigen 🔥🥶 https://t.co/30ZQWZKiYr Cooked Another Launch Video For @geteigen 🔥🥶 https://t.co/30ZQWZKiYrview source ↗
-
• twitter 2d 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 2d 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 2d 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 2d positiveBuild 👏 more 👏 backlinks Build 👏 more 👏 backlinksview source ↗
-
• twitter 2d 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 2d 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 2d 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 2d 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 ↗
-
• twitter 2d neutralThis particular chart is wild https://t.co/n68wXYj2Bs This particular chart is wild https://t.co/n68wXYj2Bsview source ↗
-
• twitter 2d positiveFuck dropshipping, Fuck claude code, Fuck building AI startups it's all for poors The easiest way to print $30k/mo with AI in 2026 is running a fake old lady on tiktok who sells vitamins to women in their 60s.... 99% of you won't do it because it's too embarrassing to admit Total tool stack to operate one of them: … Fuck dropshipping, Fuck claude code, Fuck building AI startups it's all for poors The easiest way to print $30k/mo with AI in 2026 is running a fake old lady on tiktok who sells vitamins to women in their 60s.... 99% of you won't do it because it's too embarrassing to admit Total tool stack to operate one of them: $300/mo ChatGPT $200 (automation using Dots) Higgsfield $15 (AI avatar) ManyChat $15 (the DM funnel) Gumroad FREE That's the entire infrastructure for a business that does $30-50k/mo Move 1. Build the character in Higgsfield. Pick a real older woman archetype. Chinese grandmother for cooking. Asian monk for wellness. Latin abuela for natural remedies. Move 2. Run the 14-day warming sequence. Don't post AI videos on day 1. Browse for 3 days. Comment for 4 days. Post 8 normal videos for 7 days. Day 14 start the real content. Skip this and you get shadow-banned in week 3 Move 3. Pick 5 starter products. Filter to women 38-65 categories: kitchen, home, beauty, supplements. Skip products with under 50 sales/week. Pick winners with 4+ stars and 3+ creators making sales Move 4. Write the 18-second BOF script. Hook line ("if you're over 50 and your knees crack, this is for you"). Demonstration with one specific number. CTA referencing the yellow basket icon. Product visible from second one Move 5. Automate posting 6 videos a day. Most will flop. By video 100 you'll have 1-2 winners pulling 200k-500k views. Duplicate the winners 30x. Don't tweak. Move 6. Set up a manychat trigger before day 1. Trigger keyword tied to a 4-message DM flow ending in your tiktok shop affiliate link. 31-41% click-through rate vs email at 4%. Adds $200-800/mo per page on autopilot Month 2 you'll cross $3-5k. Month 3 you'll cross $10-15k. Month 6 you should be at $30-50k from one page. Month 9 at 2-3 pages The math nobody talks about Dropshipping requires inventory, supplier negotiations, ad spend, returns, customer service. Average margin 4-12%. Average operator buview source ↗
-
• twitter 2d positivehi we are hiring applied ml intern/s requirements - strong cs + ml fundamentals - prior experience building ai agents or harnesses that actually work - high agency and first principles thinking obv - bonus points if youve worked on: rl envs, eval frameworks or verifiable systems with lean to apply just dm me or r… hi we are hiring applied ml intern/s requirements - strong cs + ml fundamentals - prior experience building ai agents or harnesses that actually work - high agency and first principles thinking obv - bonus points if youve worked on: rl envs, eval frameworks or verifiable systems with lean to apply just dm me or reply with your work, projects(github links too) and resume(optional) in person preferred (in blr) but can consider remote if youre v v good thanks and rt for good karma :Dview source ↗
-
• twitter 2d neutralBack when hackathons were pure grind. https://t.co/sNEbNmuEqF Back when hackathons were pure grind. https://t.co/sNEbNmuEqFview source ↗
-
• twitter 2d neutralThe greatest thing to happen to local ai is pewdiepie lol https://t.co/dMgdrp9ktT The greatest thing to happen to local ai is pewdiepie lol https://t.co/dMgdrp9ktTview source ↗
-
• twitter 2d neutralNo tech has embarrassed me in front of people more than Siri. https://t.co/2ZtL4hFkQy No tech has embarrassed me in front of people more than Siri. https://t.co/2ZtL4hFkQyview source ↗
-
• twitter 2d neutralhttps://t.co/4Tc530ozI4 https://t.co/4Tc530ozI4view source ↗