•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 1176–1200 of 6064 mentions
-
• twitter 18h neutralIntroduction to Verification Engineering In this video, you'll learn: → How to build an agentic loop with @testerarmy's e2e open source testing framework → Run this loop on every PR → What makes e2e different: deterministic AND agentic → The future of agentic development https://t.co/OG7ZpT5reF Introduction to Verification Engineering In this video, you'll learn: → How to build an agentic loop with @testerarmy's e2e open source testing framework → Run this loop on every PR → What makes e2e different: deterministic AND agentic → The future of agentic development https://t.co/OG7ZpT5reFview source ↗
-
• twitter 18h positivethis is absolutely INSANEEE jack dorsey, one of twitter’s founders, just dropped a completely free github repo that’s already sitting at 26.2k stars, and it’s basically an ai-agent operating system you can use to run a business here’s how it works: 1. clone the repo 2. self-host the whole thing: channels, search, gi… this is absolutely INSANEEE jack dorsey, one of twitter’s founders, just dropped a completely free github repo that’s already sitting at 26.2k stars, and it’s basically an ai-agent operating system you can use to run a business here’s how it works: 1. clone the repo 2. self-host the whole thing: channels, search, git, automations, it all lives on your server 3. add your agent to a channel like it’s a new hire, tighten its permissions, and let your team steer it live as it works save this. bookmark it. you’ll thank yourself laterview source ↗
-
• twitter 18h positiveI keep seeing people call an LLM an “AI agent” just because it can use a tool. But the LLM is only one part of the system. The model does the reasoning and decides what needs to happen. The agent harness is what actually connects everything together. It manages tools, permissions, context, memory, sandboxing, sub-age… I keep seeing people call an LLM an “AI agent” just because it can use a tool. But the LLM is only one part of the system. The model does the reasoning and decides what needs to happen. The agent harness is what actually connects everything together. It manages tools, permissions, context, memory, sandboxing, sub-agents, and the loop that keeps the agent working until the task is done. Think of it like this: - Model = decides - Harness = executes So, what happens between those two? A tool gets called. The result comes back. The context gets updated. Permissions are checked. Memory might be used. Another tool might be called. And the loop continues until the agent reaches the goal.view source ↗
-
• twitter 18h neutralhttps://t.co/fLE3sBToBM ⚡ FLASH SALE: $49/mo (normally $69) — only 5 spots, 60 mins left 👉 https://t.co/pketIk0u0f https://t.co/fLE3sBToBM ⚡ FLASH SALE: $49/mo (normally $69) — only 5 spots, 60 mins left 👉 https://t.co/pketIk0u0fview source ↗
-
• twitter 18h neutral#Drone-Powered Facade Cleaning Turns Peruvian Entrepreneur into Success Story by @Arcfunmi #EmergingTech #Technology #Innovation https://t.co/ZXqbM9aNm4 #Drone-Powered Facade Cleaning Turns Peruvian Entrepreneur into Success Story by @Arcfunmi #EmergingTech #Technology #Innovation https://t.co/ZXqbM9aNm4view source ↗
-
• twitter 18h neutralDeepSeek Harness + Ling 3.1 Flash + Claude Code Mods https://t.co/fLE3sBToBM DeepSeek Harness + Ling 3.1 Flash + Claude Code Mods https://t.co/fLE3sBToBMview source ↗
-
• twitter 18h positiveOne day you stop begging people to see your worth and finally start living like you already know it. One day you stop begging people to see your worth and finally start living like you already know it.view source ↗
-
• twitter 18h neutralI use LLMs for coding-related tasks. Nothing else. Actually, also for high-level overviews before I attempt to learn something through reading books. I find other use cases… brain-enshittifying. I use LLMs for coding-related tasks. Nothing else. Actually, also for high-level overviews before I attempt to learn something through reading books. I find other use cases… brain-enshittifying.view source ↗
-
• twitter 18h negativewoke up at 5:30 today for day 2 at the gym. it was chest day and i already forgot the names of all the exercises 😭 just know i did 4-5 of them, 3 sets each, around 15-20 reps. then went for a 5 km run after that because apparently i had too much energy left. thought i’d be dead by now, but i actually feel more energ… woke up at 5:30 today for day 2 at the gym. it was chest day and i already forgot the names of all the exercises 😭 just know i did 4-5 of them, 3 sets each, around 15-20 reps. then went for a 5 km run after that because apparently i had too much energy left. thought i’d be dead by now, but i actually feel more energetic than usual 😭view source ↗
-
• twitter 18h positiveAlarmingly, OpenAI doesn’t seem to be very focused on models They should be - the came back because of Astra and Sol - both solid models It’s time to ship a truly better model Alarmingly, OpenAI doesn’t seem to be very focused on models They should be - the came back because of Astra and Sol - both solid models It’s time to ship a truly better modelview source ↗
-
• twitter 18h neutralMy Codex Pro is renewing in 2 days... Should I continue my Codex Pro or just move to Claude Max? My Codex Pro is renewing in 2 days... Should I continue my Codex Pro or just move to Claude Max?view source ↗
-
• twitter 18h neutral"hey dot, create a plan to stop Anthropic taking all our customers" "hey dot, create a plan to stop Anthropic taking all our customers"view source ↗
-
• twitter 18h negativeOpportunities aren’t measured by tools adopted, but by turning AI into products that solve real problems and create clear market value with owned IP that scales globally. — Dr. Khulood Almani, Creative Summit 2026 Opportunities aren’t measured by tools adopted, but by turning AI into products that solve real problems and create clear market value with owned IP that scales globally. — Dr. Khulood Almani, Creative Summit 2026view source ↗
-
• twitter 18h neutralThis Opus 5.5 prompt is literally ~$5,000 motion graphics video🤯 Prompt in comment https://t.co/kCraHiB3gq This Opus 5.5 prompt is literally ~$5,000 motion graphics video🤯 Prompt in comment https://t.co/kCraHiB3gqview source ↗
-
• twitter 18h neutralNew week ~ New opportunities. https://t.co/WPMX9fg7YJ New week ~ New opportunities. https://t.co/WPMX9fg7YJview source ↗
-
• twitter 18h positivehey chatgpt dress me up in the traditional costume of the country i look like im from I guess I look Norwegian https://t.co/JumxsUGq47 hey chatgpt dress me up in the traditional costume of the country i look like im from I guess I look Norwegian https://t.co/JumxsUGq47view source ↗
-
• twitter 18h positive🚨 CODEX Users!! We will get free codex resets everyday For the next 28 days If OpenAI don't ship one meaningful improvement every single day for Codex + ChatGPT Work So basically: 📈 Improvement drops = W 🔄 No improvement = FREE RESET 🔥 28 days of Codex updates OpenAI just turned the next month into a Codex upgr… 🚨 CODEX Users!! We will get free codex resets everyday For the next 28 days If OpenAI don't ship one meaningful improvement every single day for Codex + ChatGPT Work So basically: 📈 Improvement drops = W 🔄 No improvement = FREE RESET 🔥 28 days of Codex updates OpenAI just turned the next month into a Codex upgrade marathon What would you like openAI To ship?view source ↗
-
• twitter 18h neutralEvery tip in @karpathy's post is gold. I use the HTML one a lot. When I'm learning something new or trying to understand complex code, I ask the agent to build me a visual HTML page. Here I was learning SEO and GEO. The agent turned the key ideas into an interactive page I could click through. I picked it up faster … Every tip in @karpathy's post is gold. I use the HTML one a lot. When I'm learning something new or trying to understand complex code, I ask the agent to build me a visual HTML page. Here I was learning SEO and GEO. The agent turned the key ideas into an interactive page I could click through. I picked it up faster than I would have from reading docs. https://t.co/C4PkQd3kEXview source ↗
-
• twitter 18h neutralI feel this too. Feedback loops are compressing. It’s hard to not be constantly wired with external stimulus these days. Any tips for counterbalancing this? I feel this too. Feedback loops are compressing. It’s hard to not be constantly wired with external stimulus these days. Any tips for counterbalancing this?view source ↗
-
• twitter 18h neutralSitting in a plaza alone at night with your face illuminated by Obsidian on a MacBook Pro screen at 65% brightness music https://t.co/fHBK5QnjJM Sitting in a plaza alone at night with your face illuminated by Obsidian on a MacBook Pro screen at 65% brightness music https://t.co/fHBK5QnjJMview source ↗
-
• twitter 18h positiveThought I would not be tokenmaxxing on my birthday, but ended up shipping an ASC CLI release yesterday. Another great release coming today. Enjoy the birthday gifts from me :) https://t.co/RuXh8T3xK2 Thought I would not be tokenmaxxing on my birthday, but ended up shipping an ASC CLI release yesterday. Another great release coming today. Enjoy the birthday gifts from me :) https://t.co/RuXh8T3xK2view source ↗
-
• twitter 18h positivehypergraph db is here!! HStore GitHub - https://t.co/E7gpbCBGbd some details on how it works: a group (hyperedge) is stored as its own object. every hyperedge has its own membership tree, and every node keeps a tree of the groups it belongs to. one write updates both sides in the same transaction. all of these are … hypergraph db is here!! HStore GitHub - https://t.co/E7gpbCBGbd some details on how it works: a group (hyperedge) is stored as its own object. every hyperedge has its own membership tree, and every node keeps a tree of the groups it belongs to. one write updates both sides in the same transaction. all of these are copy-on-write B+trees, and every branch carries a small summary: count, smallest key, largest key and a fingerprint. so "which groups do alice and bob share" walks both trees together and skips whole branches whose ranges can't overlap. and if two groups have different fingerprints, we know they're different without reading a single member. nothing gets overwritten. a commit copies only the path it touched and swaps one root, so readers stay on their snapshot and never wait for writers. time travel comes almost free from this, you can query an older generation directly. up to 23x faster than HyperGraphDB on shared-group queries. listing members is slower tho, coz every member carries roles, weights and validity times. ships as a single graalvm native binary, with its own query language (HQL) and a web console to actually look at the hypergraph🙂↕️ working on it more and more to address the disk space and listing members of huge hyperedges. ⭐️ it please and will love contributors on this one godspeed!view source ↗
-
• twitter 18h neutralDo you need anything else? https://t.co/SFDqLUCef8 Do you need anything else? https://t.co/SFDqLUCef8view source ↗
-
• twitter 18h positiveI launched thinking orbs on Product hunt yesterday. Turns out it made it to 11th rank. Need a few votes to make it 10. Would appreciate your help. https://t.co/GiN69zUXaa I launched thinking orbs on Product hunt yesterday. Turns out it made it to 11th rank. Need a few votes to make it 10. Would appreciate your help. https://t.co/GiN69zUXaaview source ↗
-
• twitter 18h negativeHer $4,000-a-Month Side Hustle Landed in Home Depot: ‘Not Bad for a Niche Product’ Read more: https://t.co/VyIWlOczAd Her $4,000-a-Month Side Hustle Landed in Home Depot: ‘Not Bad for a Niche Product’ Read more: https://t.co/VyIWlOczAdview source ↗