My issues with openai dots after about a day: overall: the vibes are not good, this feels directionally wrong I want to Just Talk to The Model. This tool wants you to be a plumber in a house where you're not allowed to touch the pipes dots has so much friction built in that it feels like it is not meant to be used: - I'm having to copy and paste stuff from chatgpt like it's 2022 because it can't actually see my chats - asking it to look at my codex chats similarly burned up a ton of codex usage. it should be able to just look at some files, which I would love to be able to upload but - like 8 hours ago all file attachments and the chatgpt Library stopped working. All download links the agent procures from its backend send 502s. - the agent just seems tuned to strip out all technical detail and explain things in the vaguest terms possible while burying the lede. i had to go back and forth with it like 4 times before its explanation for the failed downloads was accurate - it hallucinates. a ton. even full on tasks and threads and calls. - you have 0 visibility into what it's actually doing, which when coupled with the hallucination rate, you don’t know if things are actually getting done. feels like I am back on Poke trying to get an old version of Sonnet to tell the truth - similarly: it has no clue what it can and can't do, no docs skill or anything, i have to ask it to enumerate all its tools as if I'm jailbreaking it - it seemingly isn’t allowed to do anything on its VM, it's so locked down it might as well not be there - no tailscale allowed = no ssh into my dev box either - i gave it one summarization task overnight, while having like 20% codex usage left. I didn't even expect it to use codex for this. i woke up to 0% usage, 6!! new codex tasks, and work that failed due to some auth barrier early on, so i don't know why it made 6 tasks to keep trying - various auth requests and other popups/issues it gives me that require me to be at the computer, which defeats the purpose of having this on my phone - the model is just dumb. seriously dumb. like if this is actually Astra, it needs to be studied in a lab how they got it to act and sound like a model from 2 years ago final thoughts: they've launched a new product that wants to help you manage your work in chatgpt and codex without having sufficient access to any of the tools and data it needs from those surfaces meanwhile they keep pushing 3rd party plugins for services i don't use. i genuinely don't care about whether this MCP UX is a Plugin or a Plugin. in a good harness the models can set those up for me anyway. my most valuable data when using a new openai product is the history I've built up with openai and it's perplexing that they just do not allow this to compound at all moreover, things like OpenClaw and Hermes only work because you can actually go in and fix the problem yourself when something breaks. Muse works because Meta understood this and delayed the product until it was actually good

It's finally here! At last we have phase-3 results for retatrutide! So, did the drug join the scores of pharmaceuticals that fail at this last crucial step? If you've tried retatrutide recently, you'll realize the answer is 'no': it performed amazingly🧵

Until now, we’ve invested at the mercy of financial managers, ETFs, and single stocks promoted by grifters and algorithms. But with @supertake, you simply tell the agent what you believe in natural language: "humanoid robots are coming to every home." We call that your take. Then, Supertake connects to agents inside your existing brokerage (including @RobinhoodApp and @Coinbase) and builds a magical, auto-balancing portfolio of assets – taking countless considerations into account, from financial analysis and competitive dynamics to market cap and historical trends – and then places the trades on your behalf. And that’s just the start… (Btw: join the waitlist at supertake.com) 2/

Sonnet 5.5 improves on Sonnet 5 across benchmarks, in some cases dramatically. It’s a faster, lower-cost complement to Claude Opus 5.5, strongest at well-scoped everyday tasks, fixing bugs, and creating polished documents, slides, and spreadsheets.

echoing that something feels off in the recent oai gpt-6-sol release incl astra feeling dumber, giving up too easy, and super hard to read

Devs migrating from Fable to GPT-6 Astra:

cope. seethe. rage Welcome to the finale I partnered with the Wall Street Journal to release this article Probably the single worst hit piece ever written about @Kalshi Guess people will think twice before insulting me in public again wsj.com/finance/currencies/5…

People asking how I got $500k at 21: I just saved aggressively & invested! And a few side hustles lol I got around $20K combined from selling video game items (League accounts/boosting, Animal Jam items) long ago which I invested which turned into ~$80K USD now. Fun fact I still use the same bags/shoes and android phone which are 5+ years old. I was also employed full-time for SF startups during school which i also immediately invested the full paycheck. I also lived with my parents (nothing wrong with it!) & am now living rentfree & get free meals. People made fun of me in high school bc I wore the same outfit every day and thought I was broke 😭

hack the north

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution

Big news: S&P Global has entered an agreement to acquire OpenZeppelin. We started in 2015 with the vision of a secure, open financial system powered by blockchains and smart contracts. Ten years and $37 trillion in value transferred later, the standards and rails our team and community built carry major DeFi protocols and blockchain networks as well as the largest stablecoins and tokenized funds. With @spglobal, those standards and rails can now reach the benchmarks, risk frameworks, and institutional reach global markets already run on. Proud of the @OpenZeppelin team, everything we’ve accomplished, and everything we’ll continue to build together! openzeppelin.com/news/spglob…

It is @leolarav but I know that @leonardoalt also have done or is doing some FV. I take the confusion as a compliment. If you need an really executable and usable Lean4 SSZ look into us, it is free software and we are very collaborative. Built by a humble volunteer team of already 5 people. (like @IvanAnishchuk) We have not completed the formal verification of our implementation (although I would say it is 90%), because in @invisiblgarden philosophy we are using it as a learning tool. Ethereum Protocol Fellows and IG fellows are adding them. However, it is very fast, we implemented "toggleable caching" for the merkle tree intermediate hashes, like remarketable, using implied type classes and meta programming. The result, disabling the cache makes the code simple and easy to create proofs for it. Enabling the cache makes it very fast. Soon we will publish benchmarks. Thanks to metaprograming, it is trivial to use it, just derive SSZRepr in your struct. Zero builerplate: you get de/ser, Markle Root (with C or Lean hash), and cache that you can disable for simple proofs. Also, it works with a C implementation of sha256, or with a Lean implementation. github.com/etheorem/etheorem…