Sadat Ansari

Full-Stack Developer | AI Engineer | Polymath | Building & Breaking Stuffs

[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

[Andrej Karpathy @karpathy]

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.

[Sadat Ansari @sadat_codes]

@haider1 And LLMs also just do matrix multiplication right 😭😞

[Sadat Ansari @sadat_codes]

@shanebarakat understanding and control

[Sadat Ansari @sadat_codes]

@ramxcodes Exactly 💯

[Sadat Ansari @sadat_codes]

@AnfieldIvoire @petergouldart @quran By “AI slop,” I meant a design that feels generic and lacks a distinct visual identity, not to dismiss the effort the team put into it. The term is often used for AI-generated UIs that look common or templated. I could’ve phrased my criticism better.

[Sadat Ansari @sadat_codes]

@JadhavAjay01 @ramxcodes @Remotion Appreciate ke bajay follow krlo, 50 followers bhi nahi hore

[Sadat Ansari @sadat_codes]

@__Piyushrathore @ramxcodes https://t.co/qMX9cQANkE

[Sadat Ansari @sadat_codes]

It is basically AI doing the stuff in browser then rendering it over your video and giving u a video.

For example: You record your video. Reference the video to AI and say you want to make a motion graphic explainerm here give it some references. Also use @Remotion or @HyperFrames_ with your AI, these are tools which it takes help to create videos from drawing in browser

[Sadat Ansari @sadat_codes]

It is basically AI doing the stuff in browser then rendering it over your video and giving u a video.

For example: You record your video. Reference the video to AI and say you want to make a motion graphic explainerm here give it some references. Also use @Remotion or @HyperFrames_ with your AI, these are tools which it takes help to create videos from drawing in browser

[Sadat Ansari @sadat_codes]

@KhaliqHussainnn Bro made X his gallery

[Sadat Ansari @sadat_codes]

@buildwithsid Me who is not even getting 50 followers even after giving value :D

[Sadat Ansari @sadat_codes]

@maria_rcks CLI >>>

[Sadat Ansari @sadat_codes]

@mrymonx @KhaliqHussainnn Try getting inspirations from Dribble, Current UI looks generic AI because:
- The first Hero section is SAME like all AI generated looks. Instead Use custom fonts, graphic effects / gradient etc
- The 5 step showed from 'Write to Design' again have the same generic feature UI.

[Sadat Ansari @sadat_codes]

@Priyannkaaaa Silence before the storm

[Sadat Ansari @sadat_codes]

Did you know? Deleting a session in Claude Code’s agent view only removes the session from the list. The chat stays in ~/.claude/projects, and /resume brings it back.

⚠️ Transcripts auto-delete after 30 days by default. Bump cleanupPeriodDays in settings.json to keep them longer.

[Sadat Ansari @sadat_codes]

@thdxr @grok What is he trying to say?

[Sadat Ansari @sadat_codes]

If you have Max, try claiming from here https://t.co/JcUpD6Amma

[ClaudeDevs @ClaudeDevs]

We’re rolling out monthly Claude Platform API credits for Max and Team plans:

Max 5x: $100
Max 20x: $200
Team: up to $500, pooled

Works on any model, including Haiku 5.5, in your code or third-party harnesses.

How it works and full terms: https://t.co/qmWL6xVGwr

[Sadat Ansari @sadat_codes]

What is Anthropic cooking?

[Sadat Ansari @sadat_codes]

What a scheme 😭😭

[ClaudeDevs @ClaudeDevs]

We’re rolling out monthly Claude Platform API credits for Max and Team plans:

Max 5x: $100
Max 20x: $200
Team: up to $500, pooled

Works on any model, including Haiku 5.5, in your code or third-party harnesses.

How it works and full terms: https://t.co/qmWL6xVGwr

[Sadat Ansari @sadat_codes]

“Pretty soon all software will be open-source...”

Replit Agent reading this: 👀

[Amjad Masad @amasad]

What’s happening in the AI-powered reverse engineering and decompilation is absolutely insane. Pretty soon all software will be de facto open-source.

AI is coming for everything and everyone.