while i'm quite bullish on formal methods, i think it's worth tempering expectations and doing your own research on it (disclaimer: i am not an expert in it). it cannot guarantee your code is bug free, only that it matches the spec under certain assumptions, and the specs come from what people want, not math. as long as we build software for humans, nothing can prove that your spec is right, only you can judge. i created the /statechart skill in pstack primarily because it helps make the state machines implicit in your code more obvious and legible to you, so you can shrink the review surface and review the work at a higher level: does it actually match your intent and goal? i used this skill a ton while building my game tibo.dog, below you can see the statechart for story mode where i was able to find many bugs with it. in that sense, i think model checking (eg TLA+ with TLC) is quite useful for understanding and checking properties of your system e2e, and you don't have to write t…
The floor is in... we could go down another 10% in tech valuations, which would be the ultimate buy time for me. Every spare dollar I can find in the couch goes into $tsla $SPCX $UBER $AMZN $SHOP $MSFT $GOOG and $AAPL Here's what will happen: 1. The Dems are going to force us to exit Iran... President Trump will claim a Bush "mission accomplished!" and take the win for his legacy. 2. Inflation drops 3. Dems will come out in support of Data Centers and AI, in exchange for repealing tax cuts on the wealthy and some regulation on frontier models. 4. President Trump takes credit for brokering this deal and takes a second win for this legacy. 5. Ballroom reaches completion... @realDonaldTrump throws a year of ragers. Third win for his legacy 6. Pardon paloooooooza... autopen on fire. 7. Markets top tick and set new records. Bookmark this... and @grok please remind me of this every 1st of the month @bot
Introducing Personal Finance in Claude, in beta in the US. Connect the accounts you choose, and Claude answers your money questions in everyday language, from your own balances and transactions. Access is read-only, and Claude can't move, manage, or invest your money.
Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment. The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work. GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time. openai.com/index/introduc…
The Next Era of Notion
the team is experimenting this week at switching all our subagents to deepseek flash and using opus 5.5 only on the primary subagent
some fun slides from my upcoming talk @aiDotEngineer very excited to share how we ship crazy amounts of code (30x'd) without reading it, yet perf is as good if not better then when we launched there's a lot more to improve of course, and the ceiling is far from being reached, but given the relentless shipping speed and our high bar for polish, i think that our agent friendly architecture bets are paying off at taming the slop fun fact: ~230 people landed at least 1 PR to grok bot in october!
We recently added /storage to the desktop app! You can see how much disk space Claude is using on your computer and clear out inactive tasks and unused worktrees.
Some news: I’m joining OpenAI to lead product management for Core Products! I have a lot of respect for OpenAI for showing the world that scaling works, for bringing AI to over a billion people, and for believing great products are core to the mission. I’m excited to work with @thsottiaux, an incredible PM team, and everyone across OpenAI. Together, we’ll build agents that have your back and your team’s, and keep you in control, so you get more time for the people and work you love. Lots to learn, and lots to build. Please keep your feedback coming!
We’re sharing how our biology research team worked with Claude to map the first 3D structure of a vault particle from bacterial life. Vault particles are a longstanding mystery. They are barrel-shaped objects, among the largest protein structures found in our cells. They were first discovered by Leonard Rome and Nancy Kedersha in 1986, but their function remains unknown. With Claude, we’ve found results that might bring us closer to solving that mystery. Until now, vaults were only known in the cells of complex things like animals and plants. We have shown that similar proteins from bacteria (and the viruses that infect them) can also assemble into vaults. Finding the structures in these simpler forms of life may make it easier to investigate their function in our own cells. For our life sciences team, the project was also a demonstration of the potential (and the limitations) of using AI to accelerate science. In our full piece, we discuss how Claude was able to dramatically spe…
Computers have RAM, right? Welcome Pierre. Let’s reinvent everything
We need to reconsider our priors on code readability. Humans, compared to agents, are pretty slow at understanding large quantities of text. So in the old days, readability was important so the human could efficiently grok what was going on. So readability now comes down to: 1. Can a human, if needed, jump in and understand the code 2. Does the code use the same domain language as the human describing the code? 1 helps with observability and the occasional spot checks you need to do on important PR's. 2 helps the agent translate the words you use into code changes. In other words, readability is now a nicety, not a necessity. The way agents 'read' code is different - good agents are all about gathering data about how the code works. They'll prod around with it, execute parts of it. So 'readability' to agents really means 'verifiability'. How easy it is to mess about with that code to see it working. Let's take this scenario: - You have a huge module in your codebase that uses…
New: Give all your agents one shared brain in Notion. Now, ChatGPT, Claude, Muse, and Bot can save what they learn to the same memory and use the same skills in Notion. Learn how to Notion-pill your agents:
Pages in Grok Bot 0:15 What are Pages? 0:40 An example page 1:34 Sharing a Page 1:55 Tips: use your data 2:46 @X posts 3:44 Recap
I'm crying: We kicked off the X. com rewrite this spring and it was a massive undertaking. The old web stack from 2006 was one of the last things holding back growth & engineering velocity. With a new Android app, a refreshed iOS app, and a completely rebuilt web stack, X has finally arrived to the promised land of product development: The only constraint now is what the team can dream up.
Our security researchers built an autonomous cyber vulnerability discovery, exploitation, and patching pipeline. In a single run with an upcoming cyber model, it validated and generated patches for 948 local privilege escalation vulnerabilities in the Linux kernel at a total API cost of $1.2 million.
Today was my last day at Anthropic. I am so thankful for the time I got to spend there. I couldn't be more thankful for the time I spent and the connections I made. Will be taking some time off as I prepare for my next thing. I'll share more soon :)
Beautiful day for a big Omarchy release!
Releasing the model weights of Kimi K3.1 Pro: huggingface.co/moonshotai/Kim… We'll keep advancing open intelligence.
Images, upgraded—introducing ChatGPT Images 2.6. Now with GIFs and reference images. Plus, two new models are coming to the API with 50% faster image generation.
Omarchy 4.5 will ship with full compatibility for M1, M2, M3, and Neo! Incredible achievement from the Omarchy M team. The installer makes this so smooth, the dual boot makes it a no brainer. Apple hardware liberated. M4-6 on the way. WE CAN FIX EVERYTHING!
North Korea stole $6.3 billion from Binance by inviting one of its engineers to a job interview at a company that didn't exist. And the guy didn't even have access to the money. It took them five months and two separate hacks to pull this off. Back in June, an engineer on Binance's wallet team went looking for an AI tool and installed a tampered Homebrew package. Binance caught it, swapped the laptop and reset the passwords. Problem solved, they figured. Except by then the attackers already knew who worked on that team and what each person did. So they went recruiting. In September a different Binance engineer got a message on a real job site from someone calling himself a project director. First round was a video call with a fake HR person, who even shared a social media account full of personal photos so the whole thing felt legit. Second round was with the "CEO," who told him to download a coding assignment onto his work computer. It was loaded with malware nobody had seen bef…
With the recent wave of vulnerability disclosures, it’s a good time to take a closer look at your own code. Turn your coding agent into a team of security auditors with the open-source skill that seeded Cloudflare’s vulnerability discovery harness. The 6 phase approach: 1. Map the codebase 2. Hunt for vulnerabilities 3. Challenge each candidate 4. Record the findings 5. Verify the findings 6. Report what’s confirmed, rejected, or still needs validation Start your hunt here: github.com/cloudflare/sec…
does anyone remember how to code
