•twitter15877
listening to
timeline
15877
mentions
tracked
tracked
net sentiment
+24%
4998 positive
9734 neutral
1145 negative
volume & sentiment over time
Sep 30 – Oct 14, 2026 · Daily
sources
most discussed
—
active days
15
mentions
Showing 4851–4875 of 4998 mentions
-
• twitter 1w positiveone of the best running bits of the last 30 or so years is that ben affleck is actually really smart one of the best running bits of the last 30 or so years is that ben affleck is actually really smartview source ↗
-
• twitter 1w positiveGPT-6 Astra is getting dangerously good. Prompt ↓ https://t.co/zJZI69R3f2 GPT-6 Astra is getting dangerously good. Prompt ↓ https://t.co/zJZI69R3f2view source ↗
-
• twitter 1w positivePi 1.0 shipped with codemode ❤️🔥 Instead of 50 tool calls dumping raw output into context, the agent writes one script that does the work and returns only the answer Faster, cheaper, and the context stays clean https://t.co/9BXOcwpycV Pi 1.0 shipped with codemode ❤️🔥 Instead of 50 tool calls dumping raw output into context, the agent writes one script that does the work and returns only the answer Faster, cheaper, and the context stays clean https://t.co/9BXOcwpycVview source ↗
-
• twitter 1w positiveYou find the perfect startup name! ❌ .com is taken. What are you choosing? .ai .io .app .dev change the name You find the perfect startup name! ❌ .com is taken. What are you choosing? .ai .io .app .dev change the nameview source ↗
-
• twitter 1w positiveAre there any design tools that are excellent at helping you judge how well your design language coheres? Not just seeing how tokens apply to components. Ways to visualize if the steps in elevation are deliberate enough. Or if there's inconsistent gaps in the type scale. My dream is a tool that where you can adjust… Are there any design tools that are excellent at helping you judge how well your design language coheres? Not just seeing how tokens apply to components. Ways to visualize if the steps in elevation are deliberate enough. Or if there's inconsistent gaps in the type scale. My dream is a tool that where you can adjust a granular value, see how it impacts components, and also how it impacts the coherence of the design language.view source ↗
-
• twitter 1w positivegoing to a listening room in Toronto feels like I'm part of an underground music society https://t.co/tS4YKxw8aK going to a listening room in Toronto feels like I'm part of an underground music society https://t.co/tS4YKxw8aKview source ↗
-
• twitter 1w positive1 year ago I started posting on X 👀 best decision I ever made... https://t.co/bl0e0470aP 1 year ago I started posting on X 👀 best decision I ever made... https://t.co/bl0e0470aPview source ↗
-
• twitter 1w positiveWe'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs we… We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.view source ↗
-
• twitter 1w positiveI remember the first meeting where the team pitched the idea of putting compute in space - exciting idea! Today's successful launch with our partner @planet prototype satellite shows how far we've come...and how far there is to go. Thanks for the lift, @SpaceX, another spectacular booster landing too🚀 I remember the first meeting where the team pitched the idea of putting compute in space - exciting idea! Today's successful launch with our partner @planet prototype satellite shows how far we've come...and how far there is to go. Thanks for the lift, @SpaceX, another spectacular booster landing too🚀view source ↗
-
• twitter 1w positiveIn high school I had this class where you create a fake startup and pitch it to fake investors. I did the competition 2 years in a row. Out of like 11 groups I didn’t place top 4 once. Apparently I wasn’t “realistic” enough… https://t.co/6EtYP4UK1L In high school I had this class where you create a fake startup and pitch it to fake investors. I did the competition 2 years in a row. Out of like 11 groups I didn’t place top 4 once. Apparently I wasn’t “realistic” enough… https://t.co/6EtYP4UK1Lview source ↗
-
• twitter 1w positiveThe statue of Prometheus is finally finished. It was cast in Paris, crossed the Atlantic, and was assembled at Starbase. It took us 100 days to go from nothing to this. People of the West, we have lived through an era devoid of dreams, devoid of destiny. But the time has come to reclaim our dream of antiquity. In a… The statue of Prometheus is finally finished. It was cast in Paris, crossed the Atlantic, and was assembled at Starbase. It took us 100 days to go from nothing to this. People of the West, we have lived through an era devoid of dreams, devoid of destiny. But the time has come to reclaim our dream of antiquity. In a few months, we will start building a new city. It will be the most magnificent city in all of history. After all, the great dream of the West has always been to rebuild Rome. Come walk beside us in this endeavor. The world is waiting.view source ↗
-
• twitter 1w positive"Hey Fable, please make a cool animation" 15 minutes later. FABLE 5.5 IS SO GOOD AT THESE. HOW??? https://t.co/PS1GTkJUgd "Hey Fable, please make a cool animation" 15 minutes later. FABLE 5.5 IS SO GOOD AT THESE. HOW??? https://t.co/PS1GTkJUgdview source ↗
-
• twitter 1w positiveshill me the best video people you know in sf shill me the best video people you know in sfview source ↗
-
• twitter 1w positiveRT @RhysSullivan: genuinely feels like the future using executor v2, it's so cool i wanted to understand v2 usage, so it built a full app… RT @RhysSullivan: genuinely feels like the future using executor v2, it's so cool i wanted to understand v2 usage, so it built a full app…view source ↗
-
• twitter 1w positiveWe raised a $1M pre-seed to connect agents to the world And in the last 2 months we've launched Solari, the fastest agent infra on the market: - 2K+ developers - 100+ companies - 4x faster than Kernel, 15x faster than Browserbase - Sandboxes 1.3x faster than E2B, 1.7x faster than Daytona Thank you to every developer… We raised a $1M pre-seed to connect agents to the world And in the last 2 months we've launched Solari, the fastest agent infra on the market: - 2K+ developers - 100+ companies - 4x faster than Kernel, 15x faster than Browserbase - Sandboxes 1.3x faster than E2B, 1.7x faster than Daytona Thank you to every developer and company who's tried Solari, shared feedback, and helped us build. Grateful to our investors for believing in us this early. More to come 🚀 - https://t.co/v89Q4oCQ10view source ↗
-
• twitter 1w positive.@ElenaVerna: "AI = Average Intelligence. I'm sure we'll get to AGI someday, but for now, it's still super powerful to have at your fingertips an average marketer, an average engineer, an average analyst, an average designer. Honestly, that's better than some of the teams I've had." .@ElenaVerna: "AI = Average Intelligence. I'm sure we'll get to AGI someday, but for now, it's still super powerful to have at your fingertips an average marketer, an average engineer, an average analyst, an average designer. Honestly, that's better than some of the teams I've had."view source ↗
-
• twitter 1w positiveUp, up, and away. 🚀 Today, in partnership with @planet, we launched a prototype satellite carrying four TPUs into orbit on @SpaceX's Transporter-18 rideshare mission. This launch is the first step of Project Suncatcher, our long-term research moonshot to see whether we can one day host scalable machine learning infras… Up, up, and away. 🚀 Today, in partnership with @planet, we launched a prototype satellite carrying four TPUs into orbit on @SpaceX's Transporter-18 rideshare mission. This launch is the first step of Project Suncatcher, our long-term research moonshot to see whether we can one day host scalable machine learning infrastructure in space. Over the coming weeks, we'll gather in-orbit data on how our TPUs handle the physical stress, radiation, and thermal extremes of space. Whatever we learn, we'll use it to refine our future designs.view source ↗
-
• twitter 1w positiveKev 1.0: an open weight family of decision models you can train and run on your own. • New Kev-27B + updated Kev-9B • 64k-token document window on Kev-27B • TypeSafe SDK compatible • New fine-tuning + deployment skills so you can train Kev on your own data https://t.co/y2ajS1kwsO Kev 1.0: an open weight family of decision models you can train and run on your own. • New Kev-27B + updated Kev-9B • 64k-token document window on Kev-27B • TypeSafe SDK compatible • New fine-tuning + deployment skills so you can train Kev on your own data https://t.co/y2ajS1kwsOview source ↗
-
• twitter 1w positiveI love my founders And will proudly go to war with them anytime ⚔️ I love my founders And will proudly go to war with them anytime ⚔️view source ↗
-
• twitter 1w positiveMost of us don't have access to multi-million dollar NVIDIA gpu sleds (if you do, hit me up). But I wanted to learn how they work, so i build a 3d guide! Unified GPU / CPU systems like this are what's powering all these mega-ai DCs. Incredible what educational tools you can build with llms. Most of us don't have access to multi-million dollar NVIDIA gpu sleds (if you do, hit me up). But I wanted to learn how they work, so i build a 3d guide! Unified GPU / CPU systems like this are what's powering all these mega-ai DCs. Incredible what educational tools you can build with llms.view source ↗
-
• twitter 1w positiveonce in a while you pause the stream of tokens to read the chain of thoughts and find absolute delights like this https://t.co/0f9tfq4Qm3 once in a while you pause the stream of tokens to read the chain of thoughts and find absolute delights like this https://t.co/0f9tfq4Qm3view source ↗
-
• twitter 1w positiveIntroducing Oh-My-Hermes It is not a harness meant to replace Hermes. Instead, if you are a Hermes Agent power builder or simply want to extract top-tier, high-quality code out of Hermes, it is an essential intelligence plugin you’ll want to install. It comes equipped with pre-planning, sub-agent and bot execution qu… Introducing Oh-My-Hermes It is not a harness meant to replace Hermes. Instead, if you are a Hermes Agent power builder or simply want to extract top-tier, high-quality code out of Hermes, it is an essential intelligence plugin you’ll want to install. It comes equipped with pre-planning, sub-agent and bot execution queuing, parallel tool calling and evaluation, goal engineering and definition, excessive loop-turn prevention, per-model Hermes prompt optimization, a long-term memory system, over 110 engineering skills, agent memory cleanup skills, LLM Wiki, research tools, media file parsing, Visual QA, design capabilities, a custom TUI, and prompting skills designed to trigger tools like Claude Code or Codex. GitHub: https://t.co/g1exHwWK5E It is an open-source project crafted by resolving the exact friction points experienced day-to-day as a Hermes Agent user, and it has already earned the love of the community with over 3,000 stars. Installation takes just a single command, and model configurations can be easily handled via the onboarding flow or TUI. Install Oh-My-Hermes and make your Hermes Agent faster, easier, and dramatically more powerful that is our core philosophy. #hermes #agentview source ↗
-
• twitter 1w positiveI've been customizing Claude to look the way I wanted to for the past 2 weeks. I ended up with something phenomenal. https://t.co/2PxEzVjVr6 I've been customizing Claude to look the way I wanted to for the past 2 weeks. I ended up with something phenomenal. https://t.co/2PxEzVjVr6view source ↗
-
• twitter 1w positivei have no idea why someone built this but i'm so glad they did https://t.co/u4IX4gQeHv i have no idea why someone built this but i'm so glad they did https://t.co/u4IX4gQeHvview source ↗
-
• twitter 1w positiveI am positive this is good for society I am positive this is good for societyview source ↗