Sadat Ansari (@sadat_codes) header
Sadat Ansari (@sadat_codes) profile picture

Software Engineer | Polymath | Learning everything I'm curious about

India
Joined October 2024
Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)Photo by Sadat Ansari (@sadat_codes)
tip: don't type "use ASD-STE100" every time in every prompt just tell your coding agent "add to your global instructions: whenever you explain something or write docs, use ASD-STE100" it saves it to its own config (CLAUDE.md, AGENTS.md) and it sticks across every project
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
1
6
1,810
Sadat Ansari retweeted
A brief history of AI Coding since Nov 2025: Nov 2025: Opus 4.5 releases, OpenClaw gets built Dec 2025: community agrees that models get good enough to handle 95% of coding tasks Jan 2026: Ralph loops get popular, early efforts on loops/orchestration Feb: Everyone feels knackered, too much strategic decision-making, fears around cognitive debt begin Mar: Skills explosion as community converges around easy-to-share processes (superpowers already ahead of the game here) Apr: most SOTA devs haven't written a line of code in months May: "The unreasonable effectiveness of HTML" - more interest in richer review surfaces Jun: "Loop Engineering" wins vaguepost of the year, signals more hype around process Jul: Every talk in every conference becomes "here is my software factory" Aug: Opus 5 speaks incomprehensibly, interest in ASD-STE100 peaks Sep: Grok Bot gets popular, more interest in long-running "manager" threads which retain context and delegate work Oct: The promised speed gains haven't materialised, "dark factory" feels a long way off still Nov: No-slop manifesto releases, reading the code still appears essential TL;DR: no-one is writing code anymore, and we are still figuring out what that means
285
380
82
4,794
252,212
Square shaped status dots >>> Circular one
1
5
44
me yapping 'coding is solved' to others when someone mentions 'if claude goes down, how will u do work' 🙃
1
3
92
Building is the easy part, but maintaining isn't
“Saas is dead” “Everyone’s gonna vibe-code their own tools.” I talk about this a lot, but… you just dropped $4K–$10K building a replacement for a $25/month SaaS. And now you’ve got a server bill + AI costs to maintain it too 💀
2
2
68
Builders/Desginers, What to do when client loves slop and wants designs like these? I feel very bad that they are paying for this. How to make them understand the importance of brand identity?
2
45
The machines outlived the legacy of the man who brought them to the table.
We proudly gave @OpenAI our NVIDIA DGX-1 supercomputer to work on #AI's toughest problems. nvda.ws/2aRtOhE
2
118
Nvidia without Jensen is just a trillion-dollar company that sells shovels to people who are now wondering who’s going to keep telling them it’s a gold rush.
BREAKING: Nvidia $NVDA CEO Jensen Huang resigns.
2
57
my first post on X that hit 10k impressions 😭
genuine question for t3 code folks @t3dotcodes @theo : when you import a claude code session, why does it start a fresh session and replay the history in the first prompt instead of resuming the original one? my terminal session and the GUI thread ended up diverging.
1
1
232
sorry if it feels dumb question, what is special about @NousResearch hermes and how it is different from other harnesses? I haven't tried it, but have seen a lot of ppl using it as a personal assistant, so I first want to understand.
4
5
774
my engagement when I am not talking about tech 😭😭
2
1
3
121
genuine question for t3 code folks @t3dotcodes @theo : when you import a claude code session, why does it start a fresh session and replay the history in the first prompt instead of resuming the original one? my terminal session and the GUI thread ended up diverging.
6
1
29
12,218
Sadat Ansari retweeted
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT. We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble. You'll find it in Settings > Usage, or at clau.de/reset.
1,890
2,894
2,005
46,927
3,490,054
Finally Adobe is releasing MCP support entire suite. W @Adobe Time to cook with agents in it now 😁 #AdobeMax2026
Adobe is back, officially releasing MCP support for its entire creative cloud stack. they are back on their toes, feels exciting to see this be released in real-time in Miami. Adobe becoming headless!?
1
1
175
i said about this in the start of the month btw🥹
why is @Adobe not providing MCP for photoshop, illustrator, premium pro etc?
1
31
Sadat Ansari retweeted
I’m so glad I became an engineer (over a footballer or a doctor - other two options I had) As an engineer, with AI you can just do anything now. Open models have gotten so good I think they’re like a month behind the closed frontier now. In the last three days I’ve deleted 18 mac apps and rewritten them from scratch with my taste and preferences. This has increased my productivity and focus beyond what I expected. It’s not just software btw. I’m building hardware too. I’m again starting to lean into my electrical engineering background and having so much fun building hardware. Using Command Code to write hardware kernels that auto evolve as needed in a giant rsi loop has been such a rewarding experience. What an exciting time to be an engineer. I recommend that you build a couple of small apps to experience this. Start today.
12
4
1
118
4,409
why this gif thing is filled in my feed, everyone posting the same thing about copying and getting so many views lol 😂
1
29
Sadat Ansari 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
1,467
43,776
Sadat Ansari retweeted
The gap between an average engineer and the best engineers was never quite 10x, but it was meaningful. AI has made the gap at least 100x.
294
220
58
5,733
325,544
How many of guys know about 'meat proxy' 🌝
1
22