SDG (@thesobercoder) header
SDG (@thesobercoder) profile picture

Principal Engineer | AI Tinkerer | Contrarian

India
Joined February 2009
Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)Photo by SDG (@thesobercoder)
I'm sorry, what?????????????? Am I having a fever dream?!?!?!
97
4
2
966
94,081
SDG retweeted
BREAKING: The Riemann hypothesis is solved. There is still one problem.
JUST IN: Riemann Hypothesis has been solved. alpo.ge/remark.pdf
22
40
7
590
30,441
SDG retweeted
small updates in pstack v0.15.46 • lots of pruning, skills are now much shorter • gemini 4 neon is added as a panel reviewer it's autoupdated for grok bot / cursor users! if you want to change any of the model routing, just run /setup-pstack again x.ai/bot/plugin/9717366
138
120
14
1,948
202,603
Stop 👏
stop 👏 storing
1
190
SDG retweeted
I think a lot of people aren't using Grok Bot to its full potential, because knowing how to automate things is actually quite a difficult skill to learn. I wrote this post to break down how I approach automating anything with Grok Bot!
1,205
1,849
540
17,144
2,767,732
Frigging love this dude 😆
BREAKING: Robert Pattinson has been selected as the latest model for OpenAI, effective immediately.
1
38
6.2 Astra is here. I’ve been testing it for awhile. I think this is the worst model OpenAI has ever released. I’ll share more soon.
483
198
254
8,501
601,356
Shit just hit the fan
The #FBI issued a FLASH advisory warning that cybercriminals and state-aligned hackers are exploiting ARTEX, a super intelligence-powered penetration testing framework, to automate attacks against businesses and organizations worldwide. ARTEX can accelerate intrusions from initial targeting to privileged access in under three hours. It was used in the October ConnectWise supply-chain compromise, which exposed Microsoft 365 customer environments and involved attempted authentication against more than 2,250 downstream tenants. The FBI is urging businesses and organizations to strengthen access controls, monitor suspicious automated activity, and report potential compromises to ic3.gov. Read more here: ic3.gov/CSA/2026/261113.pdf
27
Hey @poteto I'm really interested to know your take on this I was recently asked to do something like this for a legacy product and I wanna know how the industry approaches this problem space
Replying to @omarsar0
But how else would you generate it? For e.g. let's say I want to port a legacy business application and ask an agent to generate a set of verifications that the writing agent uses to verify the accuracy of the ported business logic? You're saying it's a bad idea?
38
SDG retweeted
bring your bot to meetings! it's a great way to let them gather their own context, making your bots smarter. or if you're about to board your flight without Starlink, your bot can still attend on your behalf and take notes to get started, just ask your bot!
Grok Bot can now join meetings. Ask it questions, assign it work, or have it keep track of what your team decides.
115
39
13
1,165
103,806
SDG retweeted
one of the best ways to get the most out of grok bot is with our many connectors. the more context and tools your bot has, the more helpful it can be to your work and life! try asking bot to look at messages from your family and update your calendar for important events or look at messages from potential clients for your small business and help manage your bookings
Grok Bot on Mac can now use Messages, Mail, Notes, Reminders, Calendar, Location, and Contacts.
161
46
14
1,306
120,145
Self-hosted Claude Managed Agents is now in private beta. You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
429
882
406
15,022
1,435,114
SDG retweeted
Introducing the UI SDK.
218
435
246
6,566
895,209
Love how this launch video is about hill climbs
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
1
75
This is taking TUIs too far
1
43
OK this is massively addictive, can't believe this was a one shot prompt
I wanted to test Fable 5.2's quality with one-shot prompts without human feedback. Everything in this game is from scratch: models, sounds, textures. ~$550 at API pricing, ~2.7M output and 445M input tokens, heavily cached. Took 8 hours! Play it here: claude.ai/artifact/BGY1SztrA…
1
61
SDG retweeted
reset rolling out!
We've reset weekly limits for all Grok Bot users. Enjoy!
386
82
43
3,629
182,466
Heard the term "gardeners" from @theo today, @poteto doesn't like the term "software factory" saying we're "chefs", @mattpocockuk defends "software factory" defining it as "building automations to help agents work on products" Am I wrong in thinking peeling off the surface they are mostly the same thing with a few nuances here and there
Just wanted to defend the term "Software Factory" for a second. First, the caveats: It's bullshit. It sounds fancier than it really is. It's a bandwagon. People are using it to get you and their VC's hyped. But it's also referring to a real change. Earlier this year, most SOTA teams were using agents to work on the product. Shipping features, fixing bugs. But now, they're building automations to help agents work on the product for them. They've moved up a layer. What do we call the thing they're building? Loops? Workflows? Some other generic label? "Software Factory" is as good a term as any other. - "We're not working on the product, we're working on the factory that builds the product." - "We're not product engineers, we're factory engineers." I like it. I'll continue using it.
1
75
Damn @theo I was sleeping on T3Code man, last time I installed it was a few months back and it felt very underwhelming, but holy cow now it feels like I left behind a Honda Civic and came back to a Lamborghini PS: Now I know why you go to sleep at 6AM
29
SDG retweeted
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 tons of new verification code for it. the spec isn't your actual code so there's always a risk of drift, but so far i've had good experiences finding actual bugs with it. i tend to pair it with empirical verification (running the code) also to confirm it's real other types of formal verification like proving theorems (eg Lean, Dafny), bounded model checking (eg CBMC, Kani) etc have their own tradeoffs. proofs cover every possible input, but only for the properties specified, and it takes a lot more code/work. bounded model checking can run on your actual code, which avoids drift, but it only checks up to a certain number of steps, so it's better at finding bugs than proving there aren't any so i think in the near-medium term you'll still need to layer your codebase: constraints and guardrails (types, lint rules, api design, refactoring), empirical verification (tests, evals, real usage), and formal verification for the parts that really need it. none of these catch everything on their own, but layered together, they catch a lot more and shrink what's left for you to review but also maybe in the limit, the bitter lesson will prevail and flawless code will just be printed out perfectly every time with no bugs. even in that scenario, /statechart still seems very helpful in confirming that the agent understood your intent correctly. give it a try if you haven't already! github.com/cursor/plugins/tr…
209
163
41
2,951
244,743