@datdiddat

."-A US Citizen -".

US
Joined December 2022
Danny Datwin retweeted
Thrilled to announce that @ThePrimeagen has joined Omarchy Core to lead Agentic QA. His new Oligarchy harness will soon be vetting all our upcoming releases using @digitalocean droplets, which will host agents running on our @AIatMeta tokens. Full cricle! omarchy.org/news/2026/09/the…
324
260
87
7,827
741,527
Danny Datwin retweeted
56
2,143
78
17,380
1,682,227
Danny Datwin retweeted
this dude is 3D printing carbon fiber for Porsche and is now creating a flying car. insane
28
47
7
1,013
267,237
Danny Datwin retweeted
You've never routed like this before. @OpenRouter is bringing Jev to all of your LLM calls, so your agentic workflows never have to waste a token again. As always, faster, cheaper, more intelligent. Go build the future.
Introducing typesafe/jev-router: a cache-aware model router powered by Jev and @typesafeai The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. Here's how it works 👇🏻
103
253
49
3,756
476,341
Danny Datwin retweeted
Legacy media REFUSED to show you a SINGLE SECOND of President Trump's speech and historic state dinner with Xi Jinping tonight at the White House So here's the ENTIRE thing, from start to finish, with translations for Xi's speech DO NOT LET LEGACY MEDIA KEEP YOU IN THE DARK
2,856
35,093
1,100
119,493
9,569,923
Danny Datwin retweeted
AI in 4 simple acronyms: 🧠 LLM = Brain 📚 RAG = Knowledge 🤖 Agent = Action ⚡ MCP = Connection Understand these 4 → AI makes a lot more sense. Save this. 🔖 Follow @mayaislam_ai for more
3
170
2
655
15,065
Danny Datwin retweeted
Foundations of Large Language Models: arxiv.org/abs/2501.09223 [277-page PDF]
60
408
24,776
Danny Datwin retweeted
In the Middle Ages only the priesthood could access the Word of God because only they could read Latin. Now only the AI priesthood can access the Mind of the Superintelligence because only they can interpret its weights. But the printing press is coming: tensor-logic.org
18
77
7
557
21,837
Danny Datwin retweeted
SpaceX's Bots Collection (56) PRT I 1. General (6) . Chief of Staff -> x.ai/bot/sc0a0ec3ce9c6758241… . Executive Assistant -> x.ai/bot/sf813cbd3aadad1cfda… . Presentation Designer -> x.ai/bot/s25997c2d0308b4e760… . Daily Briefing Writer -> x.ai/bot/sb94d44175e650dbb70… . Inbox Manager -> x.ai/bot/s4f048c7b7da9e010c2… . Status Report Writer -> x.ai/bot/sde2c69536d2f2564fe… 2. Sales (10) . Account Research Specialist -> x.ai/bot/sa7d7f82d0068c2367a… . Deal Desk Coordinator -> x.ai/bot/sb434ef300dea2b88aa… . Meeting Prep Buddy -> x.ai/bot/s445a0c9a2ca4bea772… . Prospecting Plan Builder -> x.ai/bot/s8b59eb62f90871ac5c… . Sales Call Coach -> x.ai/bot/s8173b3a9c49917de5b… . CRM Operations Manager -> x.ai/bot/s162b4ed38d6cf1d567… . Deck Updater -> x.ai/bot/s2a289081613e5e361c… . Pipeline Analyst -> x.ai/bot/s98af8b9dcde521e1a9… . Renewal Desk Operator -> x.ai/bot/s4c86a54f1886680964… . Sales Outbound -> x.ai/bot/s8ff03023f140bab479… 3. Marketing (13) . Community Operations Manager -> x.ai/bot/seb9d6ba6765c641139… . Competitive Intelligence Analyst -> x.ai/bot/sa2d131975aaab07e43… . Internal Communications Manager -> x.ai/bot/s066a9145d936e74d0c… . Marketing Calendar Owner -> x.ai/bot/se318a72a31fad75c27… . Newsletter Writer -> x.ai/bot/s5d2839123b973b4480… . Paid Media Creative Strategist -> x.ai/bot/s45471f3a8af234c130… . Social Media Manager -> x.ai/bot/s634cb1edf26493e86b… . Compelling Events Monitor -> x.ai/bot/sdeb02761a9d185e589… . Event Guest Screener -> x.ai/bot/s47ebc74c9fcf9359b5… . LinkedIn Campaign Manager -> x.ai/bot/s4d10d16bdbe2391aa7… . Merch Fulfillment Operator -> x.ai/bot/se479952f3c9e373dfd… . Paid Media -> x.ai/bot/s59facc90a46a8b4f59… . SEO / AEO Auditor -> x.ai/bot/sb6d579c33f7a32d0e7…
🤖 Made with AI
15
63
3
485
34,776
Danny Datwin retweeted
Jev + Grok Bot is the best agent setup I've built so far it's cheaper and faster than 95% of agent stacks i've seen, and the setup takes just 5 minutes: your prompt → Grok Bot → Jev decides → Grok Bot acts → result step 1 → go to @typesafeai and create an API key. don't paste it into any chat step 2 → ask Grok Bot to save it as TYPESAFE_API_KEY in the secret field step 3 → have Grok Bot install typesafe-sdk on its Agent Computer and run a quick system_one test with one Choice question step 4 → ask Grok Bot to build a small usage lab: router, dry-run mode, config and logs. or just clone my repo below step 5 → add a skill called jev-usage-router: before opening a browser, starting research, retrying a task or spinning up another bot, it asks the router first and follows the answer step 6 → run it in shadow mode first and read the logs. switch to active only once you trust the calls. keep a kill switch: bypass Jev or set enabled: false step 7 → go active. Jev picks the route, Grok Bot carries it out, and anything irreversible still waits for a human i've been running it on routine tasks and the difference is hard to ignore there are a hundred ways to use this pair, so the real advice is to set it up early and start learning where it helps grab the setup, then read the full article below ↓
39
93
10
957
132,483
Danny Datwin retweeted
Elon Musk's Grok just did a full day of sales work in 16 seconds. It cost 41 cents. It went through 3,412 people on X, LinkedIn and YouTube and picked the 186 most likely to buy. The rest were stuff like bots, students and lofi channels. Then it wrote each of the 186 a message. All you do is click send. Companies pay a sales rep $155,000 a year to do this by hand. The trick is a new AI called Jev that plugs into Grok. It came out 7 days ago. It was built by one of the guys who made ChatGPT, and almost nobody has access yet. Setup takes 9 minutes. Watch the video, then read the article below.
22
63
4
452
97,181
Danny Datwin retweeted
LLM, RAG, AI Agent & Agentic AI
15
253
5
1,248
56,143
Goldmine for AI Engineers! 📌 If you're learning AI, ML, LLMs, or AI agents, don't waste hours jumping between random tutorials. These are 10 repositories I'd actually keep bookmarked - from Python fundamentals to ML, LLMs, agents, and production AI. 1. Python - 100 Days jackfrued/Python-100-Days A 100-day Python learning path covering fundamentals, data analysis, web development, and more. GitHub: github.com/jackfrued/Pyth… 2. Generative AI for Beginners microsoft/generative-ai-for-beginners A practical introduction to building Generative AI applications. Covers: • LLM fundamentals • Prompt engineering • RAG • AI agents • Fine-tuning • AI application development GitHub: github.com/microsoft/gene… 3. LLMs From Scratch rasbt/LLMs-from-scratch Want to understand what's actually happening inside an LLM? Build one step by step. Covers: • Tokenization • Embeddings • Attention • Transformers • Training • Fine-tuning GitHub: github.com/rasbt/LLMs-fro… 4. Machine Learning for Beginners microsoft/ML-For-Beginners A structured 12-week, 26-lesson curriculum covering classical machine learning. A good starting point if you want ML fundamentals before jumping into LLMs. GitHub: github.com/microsoft/ML-F… 5. OpenAI Cookbook openai/openai-cookbook A collection of practical examples and guides for building applications with OpenAI models. Useful when you want to move from: Learning → Building GitHub: github.com/openai/openai-… 6. Stable Diffusion CompVis/stable-diffusion Interested in generative image models? This repository contains the original Stable Diffusion implementation and research code. GitHub: github.com/CompVis/stable… 7. AI Agents for Beginners microsoft/ai-agents-for-beginners A practical course for understanding and building AI agents. Covers: • Agentic AI • RAG • Agent frameworks • Tool use • Multi-agent systems GitHub: github.com/microsoft/ai-a… 8. AI for Beginners microsoft/AI-For-Beginners A structured 12-week, 24-lesson introduction to AI. Covers: • Neural networks • Computer vision • NLP • Deep learning • Classical AI GitHub: github.com/microsoft/AI-F… 9. LLM App pathwaycom/llm-app Focused on building practical LLM applications. Explore: • RAG • AI pipelines • Enterprise search • Real-time data • Vector search GitHub: github.com/pathwaycom/llm… 10. Segment Anything facebookresearch/segment-anything A foundation model for promptable image segmentation. Worth exploring if you're interested in computer vision and multimodal AI. GitHub: github.com/facebookresear… Don't bookmark all 10 and forget about them. Pick based on where you are: Python → Python-100-Days ML → ML-For-Beginners AI Fundamentals → AI-For-Beginners LLMs → LLMs-from-scratch Generative AI → Generative-AI-for-Beginners Agents → AI-Agents-for-Beginners Building → OpenAI Cookbook / LLM App Computer Vision → Segment Anything Pick one. Build something. Then move to the next.
32
231
6
1,049
61,636
Eagle( democratic party) vs Chicks( liberal voters)
老鹰🦅吃🐥,一口一只,这么危险的大家伙小鸡仔🐥却还当是它妈
76
Danny Datwin retweeted
HOW THE RICH DO IT (THIS IS HOW THE WEALTHY PROTECT WHAT’S THEIRS)
51
2
269
8,581
Boy on a Dolphin (1957) marked Sophia Loren’s American screen debut. It was also the first major Hollywood production filmed extensively in Greece, showcasing the Greek islands to international audiences and having a positive effect on tourism. Cary Grant was originally supposed to be her leading man. He had already begun filming when, just four days into production, he learned that his wife, actress Betsy Drake, had survived the sinking of the Andrea Doria, an Italian ocean liner that sank off the Massachusetts coast in 1956. Grant immediately left the production to be with her. Grant was replaced by Alan Ladd, whose height difference with Loren reportedly meant that she sometimes walked in a shallow trench so Ladd would appear taller, while he stood on a box in another shot. Loren and Grant also appeared together in another 1957 film, The Pride and the Passion. And on her special day, Happy Birthday, Sophia Loren!
37
318
12
4,773
735,961
Danny Datwin retweeted
this man makes me appreciate art 👏
22
324
10
3,423
125,613
This Knot Is a Camper’s Secret Weapon!
2
88
469
28,014
Danny Datwin retweeted
This is the future we shall bring into being
32,522
40,881
9,769
333,300
95,804,953
Danny Datwin retweeted
JEV JUST MADE HALF OF AI ENGINEERING OBSOLETE IN FIVE DAYS. a model that cannot write one sentence, cannot code, cannot reason - 200x faster, 400x cheaper. somebody already rebuilt claude code's compaction on top of it and got 4,575 stars in five days. 5 rules before you wire it in. jev does not generate text. you hand it state and typed questions, it hands back a choice from a set YOU defined, plus a confidence score. it physically cannot return something off-schema. that is the whole product. -> SEPARATE the deciding from the generating before you touch anything else. most agent loops burn a full generative call on "which tool" and "should i retry" - questions with 3 possible answers. you are paying frontier rates for a multiple choice test. -> SET your confidence threshold BEFORE you ship, not after the first incident. the calibrated probability is the actual feature here. no threshold means you built a fast oracle and then trusted it exactly as blindly as the slow one. -> LOG the confidence next to the real outcome, every time. a calibration score that drifts is invisible until you have the paired data. "it was 0.9 confident" means nothing if you never checked what 0.9 cashed out to. -> TREAT the benchmarks as marketing until someone else runs them. the speed numbers are self-reported and the accuracy reference is an AVERAGE of two frontier models. that is the vendor grading the vendor. -> STEAL the pattern from fast-jev-compaction, the claude code plugin. it kills the summary step entirely - every tool call and result gets SCORED in one fast request, stale ones dropped or truncated, everything it keeps stays VERBATIM. no summary means no summarization lies. that is the whole shape: decide what survives, do not rewrite it. third time this year i have ripped a generative call out of a routing step and the loop got faster every time. would you let something that cannot explain itself decide which half of your context gets thrown away
21
34
1
272
45,523