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

Principal Engineer | AI Tinkerer | Contrarian

India
Joined February 2009
SDG retweeted
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.
265
57
113
2,562
83,955
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
41
13
1,148
89,505
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.
159
48
13
1,295
107,917
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.
428
882
403
15,071
1,423,227
SDG retweeted
Introducing the UI SDK.
217
434
242
6,564
879,869
SDG retweeted
reset rolling out!
We've reset weekly limits for all Grok Bot users. Enjoy!
386
82
43
3,631
175,823
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
161
40
2,946
238,751
I sometimes wonder how grilling has changed my brain Probably a huge benefit - being able to reach a shared understanding about a topic is hard, and practice is good
72
12
6
748
56,690
Everything's changed. Here's what I would do if I were starting from scratch getting into software engineering.
42
71
12
912
87,741
SDG retweeted
maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis
796
434
300
11,199
1,443,120
Replying to @mattpocockuk
@mattpocockuk deserves some sort of award for all the skills he is sharing with the world. If he isn't already he should totally be a @github star or something.
11
2
116
16,921
Super excited to be interviewing @poteto, live, in ~48 hours on YouTube. We'll be nerding out about skills, high-velocity software factories, and learning SOTA techniques for shipping with agents. This Friday - 9AM PT. Don't miss it! youtube.com/live/MN9dGgmLyso
127
143
50
3,511
252,217
Still can’t believe some people consume 100k+ in inference in a month and produce absolutely nothing of value with it
38
14
3
601
18,851
22
212
12
4,906
186,081
who did this
78
275
69
4,920
329,491
Anthropic has no small models that are worth using right now. OpenAI has no large models that are worth using right now. Google has no models that are worth using right now.
556
483
142
14,525
807,958
SDG retweeted
im late to the loops discourse but from what i'm seeing it's mostly about creating a loop from your asshole back into your own mouth?
128
67
15
2,390
110,782
Meet Gemini 3.5 Flash! ⚡️ It's fast, great for building rich UIs + agents and is stronger from coding to long-horizon tasks and multi-step workflows.
30
27
2
273
43,728