@dharmeshba The last line is super exaggerated. Their systems quality is quite poor. Sahamati uses their CRM system and I could never login nor reset password. All for indigenous systems but we need more brain power there not PR power.
@kishen_h@coderUzumaki@shaandelhite What do you mean “past issues”? The paper leaked a month ago. Start holding the party in power for the last 12 years accountable.
@coderUzumaki@shaandelhite Yeah and it’s the government’s fault that they cannot even conduct a test without leaks and force the students to repeat it. Only someone who lacks empathy will blame the student in this case. You should seek help.
@clairevo As with anything in life, working with kids at home you’re going to have good days and bad days. During covid, I had my bottle-feeding daughter in my lap while doing customer calls and my wife used to breast pump while working as well. Definitely a skill issue.
@SToyota2026@sabeer Road minister makes broken roads and concerns himself with mixing water guzzling ethanol in fuel. Railways minister has sat through 2 stampedes, 3 derailments, and many cased of hooliganism / vandalism. External affairs minister has, alongwith the PM, lost our energy sovereignty.
@yogashar99@sabeer See this is exactly the point he’s trying to make. You are so blinded by the BJP that topics paper leaks, contaminated water, crony capitalism, unrelenting fuel prices, falling Rupee… just don’t matter to you. Hold the current government accountable for once!
@upamanyuacharya I don’t think it’s a zero sum game. The compute and service to run the model is useful to build. But without a sovereign model, we are at the whims of an increasingly hostile country who won’t think twice before banning access to the tech.
@nammayatri I don’t understand the point of your service. Tried to book Uber premium but wasn’t getting any cabs. Rate 400. For the same distance, the Sedan Premium was 507 on Namma Yatri. I booked anyway.
The cab I got is dirty and the driver refuses to turn up AC. Useless.
@Kizmyaaz001@PriyankKharge@digvijaya_28@RSSorg@INCIndia What if I start such an org tomorrow? Would you believe me? By what constitution is RSS authorised to “raise an army”? Who defines their power? Their limitations? Who controls them?
A shadow entity running a para military operation doesn’t have a place in a democracy.
@Kizmyaaz001@PriyankKharge@digvijaya_28@RSSorg@INCIndia Kushal, I am all for service to the nation but when it comes to national defence I trust our army more than RSS. I am sure you do too.
Any large body that can raise an army on the demand of their leaders should be regulated to ensure they work for the good of the country.
@QasimRashid Just tax the gains on the current market value pledged at the time of taking loans. Should be deducted at source prior to disbursements. At maturity, if the market value is lower than the market value when it was pledged, the losses can be offset against future taxes.
The takeaway from Fable 5 being BANNED by the government: GET GOOD AT LOCAL MODELS SO YOU HAVE 100% CONTROL.
My entire weekend was going to be building my craziest ideas with Fable 5. That's now cancelled.
So instead of building with Fable this weekend, I've decided I'll go deep on local models:
1. Start with the runtime. Download Ollama or LM Studio first. This is the thing that actually runs models on your machine.
2. Match the model to your hardware. A model's size is measured in billions of parameters (7B, 32B, 70B). Bigger is smarter but needs more memory. Rule of thumb: a 7B model runs on almost any laptop, a 32B needs a good Mac with 32GB+ RAM, a 70B needs serious hardware like a DGX Spark or a maxed-out Mac Studio.
3. Know which model for which job. Qwen 3 is the best all-around choice for most tasks. DeepSeek for reasoning and coding. Gemma 4 when you need something tiny that runs on a phone. Llama when you want the biggest community and the most fine-tunes.
4. Quantization. You can shrink a model to run on weaker hardware with barely any quality loss. Look for versions labeled Q4 or Q5. This is how a model that "needs" a server runs on your laptop. Learning this one concept changes everything.
5. Connect it to your agent. Point Hermes or your agent stack at a local model.
6. Context window is your real constraint locally. Cloud models give you huge context for free. Local models make you pay for it in memory. A bigger context window eats RAM fast. Keep your sessions tight and your prompts lean or your machine chokes.
7. Learn to give local models tools. A smaller local model with web search, file access, and code execution beats a giant model with none. The capability gap closes fast when you wire up the right tools. The model is the engine but the tools are the wheels.
8. Fine-tuning is more accessible than you think. You don't need this on day one, but know it exists. You can take an open model and train it on your own data so it gets good at your specific domain.
I'll probably do a breakdown at some point on this @startupideaspod if people are into it.
The lesson from this ban is basically don't build your entire workflow on something that can disappear with a single letter. Own part of your stack. Local models are insurance.
It reminds me when people realized they don't own social media accounts. And then you saw people build email lists etc.
I remember running a startup and my biggest traffic source was organic FB. All of a sudden, algo changed, and I lost 99% of my traffic.
Same sorta moment (but bigger) for AI.
This is a wake up call.
@Rashtra_doot@TARUNspeakss Also, please relax a bit. If you want to have an adult conversation, I can do this all day. Adults don’t need to insult to get their point across though.
@Rashtra_doot@TARUNspeakss One thing’s for sure though: our country has historically stood for peace. It has historically been regarded as a strong power. I feel we’re moving in the wrong direction at the moment, and as a concerned citizen, I’m going to point it out. Doesn’t make me any less of a patriot.