Ajeet Sinha (@og_defaultcoder) header
Ajeet Sinha (@og_defaultcoder) profile picture

Lead Software R&D Engineer, Software Division, Sumuri Forensics. Created Forensics Operating system and forensics tools for all major OS.

New Delhi
Joined October 2009
There is no substitute for the person who Knows What To Do.
1,317
4,856
482
41,388
3,002,605
Ajeet Sinha retweeted
Formal verification is the Rust of software correctness. Most do not understand it, but just as people started shipping Rust because LLMs made it easier to write, we are now writing formal specifications because LLMs can generate them. The problem is, if you do not understand what you are writing, you can never be sure that it is "correct".
50
27
4
452
31,257
I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.
873
479
436
10,282
1,665,691
Ajeet Sinha retweeted
There is unlimited demand for people who can explain difficult things in simple language.
101
163
20
1,330
39,287
software engineering really just feels like fine tuning CI/CD at this point
25
28
3
497
14,933
Ajeet Sinha retweeted
With AI, a single person with high clarity can outdo a team that lacks it. Before, there was still a chance to catch up; now, there is none.
55
78
7
1,466
43,877
Ajeet Sinha retweeted
I don't think most programmers actually hate neither product nor project management. What they hated was slow feedback loops! Dealing with weird power dynamics and office politics! Give them the power to MAKE SOFTWARE at the speed of agents, without all the nonsense, and it's ✨
15
6
3
226
15,842
Ajeet Sinha retweeted
I sympathize with programmers who worked on systems they never cared about, for customers they didn't connect with, and took all their working joy from the mechanical act of turning tickets into code. You have to care about the software to be excited about making it w/ agents!
162
258
57
4,501
207,707
Ajeet Sinha retweeted
Every software developer should own a potato PC. It's the easiest way to ensure your application is fast enough. Put your agents to work within it and watch the weight drop. There's no reason a machine from ten years ago shouldn't fly like superman.
348
247
85
6,452
351,865
Ajeet Sinha retweeted
"Some men aren't looking for anything logical, like money. They can't be bought, bullied, reasoned, or negotiated with. Some men just want to watch the world [bloom]."
51
104
14
1,843
139,467
Ajeet Sinha retweeted
The limiting factor of software engineering has never been code production. It is complexity management.
105
496
87
4,287
302,500
Ajeet Sinha retweeted
Every developer thinks they’re “almost done” once they’ve completed about 80% of the work. A lesson I keep learning over and over again: the final 20% usually takes 80% of the time. You ain't done until you are.
79
35
12
485
21,905
Ajeet Sinha retweeted
Excellent software takes time. It requires smart people to care deeply about the product and to obsess over the details. To debate passionately about the details big and small. To spend time deeply thinking. Nothing about this has changed.
28
62
10
473
16,290
Ajeet Sinha retweeted
The best engineers I've met all shared one trait: They knew a little about a lot of things. Not experts in everything, but they had working mental models of databases, protocols, design choices, and how different systems solve problems. This kind of breadth didn't come from their day job. They were always interested in new things, so they read articles, watched talks, and looked into interesting topics when it wasn't related to their current work. The payoff is huge. When you've seen how a lot of different systems solve their problems, you start drawing parallels and connecting dots other people can't. That's where out-of-the-box solutions actually come from. And it doesn't take all your weekends. 30 minutes every weekday, on something you genuinely find interesting, is enough to become a much better engineer. The hard part isn't the time. It's the consistency. But once it becomes a habit, complex topics stop feeling intimidating, and you find yourself navigating the whole landscape with ease.
64
190
23
1,752
83,125
Ajeet Sinha retweeted
When software was expensive - thin, horizontal, best-of-breed software stacks extracted rents across every business. Now that software is cheap - value moves to vertically integrated businesses that deliver opinionated end-to-end experiences.
430
949
187
13,009
864,680
Ajeet Sinha retweeted
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
2,526
4,020
1,504
50,318
4,485,768
Ajeet Sinha retweeted
Our job is to solve problems, not write code
I don't fully understand why programmers seem to be the ~only group of people not angry that their jobs are being automated.
211
1,174
93
14,990
670,569
Ajeet Sinha retweeted
The new development cycle in one image.
225
837
258
11,379
899,138
Replying to @kushsaraiya
1. Don’t allow the specs to shape the design. Specs describe behavior, not structure. 2. Don’t spec much up front. Work in short bursts of specification and implementation. (Agile). And then allow your experience with the result of each burst to inform the next spec. In other words. Encapsulate behavior and rely on intense feedback.
2
8
84
4,960
Replying to @plainionist
A firm, language agnostic, grasp of the basics. Coupling, cohesion, naming, module and function size, dependency management, unit testing, acceptance testing, etc.
6
12
152
6,065