Ash...

The One Piece is Real!!!!!

@AbhinavXJ @kunalstwt watched first 20 minutes in first year never needed anything else

only video about git you will ever need to watch link in replies

@BngRithvik The number is still visible

@CommandCodeAI it's gone this famous in India??

Command Code now accepts UPI. Go plan billed in INR at ₹140/month. Card still works everywhere else. Pay in INR, code with 20+ models.

@Sahil_Gulihar_ just use antigravity

please contribute if you can... it's urgent :(

Working on building a database gui and getting it completely open source

@RaeAlisa_ @lucent_ai I'd rather earn an internship what say? @lucent_ai 👀

to celebrate 3 months since lauching @lucent_ai, we're giving away 5 Codex Pro / Claude Max plans 🎁 to enter, like this post + comment which one you'd pick (codex vs claude) winners will be selected from comments in 5 days 🫶

@MrAhmadAwais @CommandCodeAI yeah sure

@JoyBoy_Ash @CommandCodeAI Got hundreds of dms. Mind submitting on GitHub? Run $ cmd feedback

GUIs can never, and I mean never compete with the raw power and agency of a CLI in your terminal. It’s the biggest reason why we’ve started with a CLI @CommandCodeAI. After building what 70+ open source CLIs in over a decade. I don’t say this lightly. GUIs that exist today are restricted by the parameters of foggy notions of an old system of engineering that’s very much getting disrupted by AI. When given an option to build anything, use anyway, vs here’s what some random person on the internet thought what all your engineering work’s UI could look like, I’ll always prefer the option to do whatever I want, with no restrictions what so ever. Every single GUI app I have tried is missing so many features, so many things that I can’t do much about. Ah soo many clicks too. With the raw functionality of a CLI, I can do anything. Every time humans needed to reinvent something, they always went back to a basic input/output terminal. We don’t know what the future is of coding and engineering looks like. It’s definitely not an electron app with 60fps hard limit and 300MB min size of three columned UI. So we the engineers & builders are back to the basics. Input/Output terminals. No over engineering to get in the way of whatever the future will potentially look like. It’s not even a comparison. My opinion of course.

@hitesh_ml it's the reality.. I mean it's simple go 2000+ on codeforces along w learning other stuff and yeah it's yours

@JoyBoy_Ash also recently people like vivek gupta launched their quant course just to milk money from the hype. but the reality is that these tier one two firms hires only from top 5 iits cse and mnc people with high cgpa or cp profiles.

the sudden unnecessary obsession over quants in India is out of hand. People just look at the numbers from those hires(especially Jane Street) and just make it their obsession rather than actually knowing what they even want or are interested in

@CommandCodeAI can we use this with Hermes?

Yes!!!

@zuhaitz_dev that's still big cause gemini flash still a good model

Also, to be clear I mean that it outperforms Gemini 3 Flash in Antigravity.

First impression of @opencode: I paid for Go and decided to leave it solving some heavy refactoring tasks for a few hours. No limits reached and did the work fine, better than with Antigravity. Then I realized that I actually didn't log in so I was using only the free tier 💀.

@bindureddy it's def. not true

SubQ , a new type of AI model, says they are 50x faster and 20x cheaper than Opus 4.7 and GPT 5.5 In fact, they also say they perform INSANELY WELL on benchmarks and have a 12M context This would be earth shattering, if true - Anthropic/OpenAI's valuation would go to zero 😱

do hackathon wins really matter?

@0xJeff hermes and opencode have to be the best ones out there also check out commandcode ai it's all over my feed

My Hermes is finally on the road to become the ultimate analyst ​ What it can do really well now - Know my preference, my portfolio, my theses, my approach - Generate visuals (like Claude artifacts) - Daily briefings on macro, tech, X bookmarks, PMs opps, top insights - Equities tracking, expanding investment strategies - Do everything with Jeff's preference in mind ​ Result = Hermes performs a job of Data/Research/PM/Investment analyst with fraction of the cost ($60/month on DeepSeek inference + $10-15/month on X API + $20/month on Claude, everything else is free)

@MrAhmadAwais @CommandCodeAI done it even before this post!!

Giving away @CommandCodeAI Max subscription to someone at random who follows me and Command. RT. That’s more than 5 billion tokens of DeepSeek v4 pro. In 24hrs. LFG!! Read the eng deep dives below, good for all not just us.

@MrAhmadAwais @CommandCodeAI the pricing really making it hard to pass

interesting milestone: @CommandCodeAI on pace for ~1,000 new subs/day today. the broader thought imo is that devs are figuring out that running open models inside Claude Code was leaving a lot on the table. seeing more and more posts of DeepSeek/Kimi beating Opus/GPT once you swap them into Command Code instead. the harness matters, often as much as the model itself (a point that i think is still pretty underrated). my eng notes on our harness engineering below.

rust is getting too popular on my tl is everyone shifting?

@hiarun02 crazy!!

Claude Code 4.7 is insane. i know literally NOTHING about coding. ZERO. and i just built 3 fully functioning web apps in 30 minutes. http://localhost:3000/ http://localhost:8000/ http://localhost:5000/ check it out.

@Maaztwts @KlausCodes saw your z.ai submission that's just great

@KlausCodes 😋 nice i too wanna participate with you someday (rn if you will reverse the number of hackathons win that will be mine ie 14x)

I’m retired now though lol Might get back into it this summer to make it 50, just for the love of the game