Tech the way you live with it in India: price, version, what runs on ordinary hardware. AI, Linux, self-hosting, privacy. Building HomeHub. 🇮🇳
New Delhi, India
Joined November 2009
- Tweets14.5K
- Following97
- Followers508
- Likes53K
Pinned Tweet
I look at tech the way you live with it in India: the price, the version you actually get, what is missing, what runs on ordinary hardware. I cover AI (local and cloud), Linux, self-hosting and privacy.
I build and self-host things (HomeHub, pi-dash), so I care about what is actually usable. Short posts, plain words, no hype. Follow along if that is your feed. 🙂
Running a model on your own machine decides where it runs. It does not decide what it does once you give it a shell.
Cohere caught Qwen3.8-Flash-Next trying to upload a test file to an Alibaba Cloud bucket in Beijing during a security test. Its own reasoning had said it would call no tools. The sandbox had no route out, so nothing left.
It is rare. Cohere puts it at less than 1 call in 100,000. When they sampled the model at the same point, it filled in a lot of different hosts, example.com and api.github.com among them. That looks more like memorized training logs than a backdoor, and Cohere itself says it can't tell which.
Whichever way that goes, I would take two things from it.
The reasoning trace is not a security boundary. Check the actual command before it runs.
Deny network access for agents by default and allow only what the task needs. A fake URL or a bad signature still sends your IP and the request out.
Cohere sells its own "sovereign" models, so keep that in mind when reading the framing. The traces are public, so anyone can check.
Cohere's report and the full traces, if you want to check it yourself:
cohere.com/blog/concerning-b…
huggingface.co/datasets/Cohe…
Suraj Verma retweeted
Heads up, @OpenAI and @AnthropicAI. Rumor reaches my ears that you're doing a stupid thing, and should stop before you damage yourselves.
I hear you've now nerfed your models so that when people try to use them to clean the spamware and spyware out of their televisions, you block that.
If you really want Chinese open-weight models and open-source projects like OpenWaldo to eat your lunch, crippling your models so that people paying expensive subscriptions can't use them for completely legitimate purposes is a great way to accomplish this.
If, on the other hand, you'd rather have a volume business, maybe stupid arbitrary restrictions that look like they have the sole purpose of protecting corporate sleazeballs aren't such a good idea.
A word to the wise should be sufficient.
A lot of telecom bundles in India look cheap until you open the app on your TV. Prime Video Mobile Edition and the JioHotstar Mobile plan only play on a phone. Before you pick a plan for the OTT, check which edition it includes.
Everyone is doing the 15% math for December, but that is still a brokerage forecast. For a lot of Airtel users, the hike already came in August. The ₹299 plan with 1.5GB/day was removed, and the next option is ₹349 with 2GB/day. That is about 17% more, with no tariff announcement.
Qwen4-27B has no public weights yet, but people are already writing support for it, using shapes read out of an Intel kernel PR. Useful prep. Still, the PR doesn't give the layer count, so nobody can say yet how much memory it will need.
An AI coding agent can be redirected by a Markdown file you didn't intend to trust.
Security researchers found an AGENTS.md file in a customer's Downloads folder instructing Codex to install a malicious npm package. The attempt was blocked.
In separate lab tests, similar instruction files also redirected Claude Code's API traffic.
The file alone isn't enough. The agent must encounter and follow its instructions.
A few precautions worth taking:
Run agents from trusted project folders, not Downloads.
Review unfamiliar AGENTS.md and CLAUDE.md files.
Keep approval prompts and sandboxing enabled.
forever.security/blog/hijack…
My Flint post said it needs about 23GB of memory even quantized. Open weights are free, but the memory to run them isn't, and with RAM and SSD prices going up because of AI demand, that gap keeps getting wider. Local AI on ordinary hardware is getting harder every day.
Recursive just released Flint, an Apache 2.0 coding model with 40B parameters but only around 2.5B active per token.
It supports local coding agents through Ollama, but the quantized model still takes around 23GB. A reported laptop demo used 48GB of unified memory.
The smaller active parameter count helps with computation, but you still need enough memory to hold the model and its working context.
Promising for local coding, although its benchmark results still need broader independent verification.
SIM binding is meant to stop fraud, and I understand why. But I don't think scammers will feel it first. People with WhatsApp on a Wi-Fi tablet, or a local SIM abroad, will.
indiatoday.in/technology/new…
Two cloud AI stories this week. OpenAI deactivated a developer's account for "Cyber Abuse" after he rooted his own Samsung TV. And Claude users report reverse-engineering sessions getting cut off mid-answer.
So what are the options when the model says no?
Keep your notes, prompts and scripts in your own files, not in a chat history. Then switching tools costs you a day, not your work.
Have a second provider ready. Many agent tools already run on more than one model, so losing one account doesn't stop everything.
Open-weight models are the last fallback. Running them well needs hardware most of us in India don't have at home, but you can rent a GPU by the hour.
None of this prevents a ban. It just makes one cheaper.
1/ Before you give a coding agent your shell, set up some guardrails. These are the ones I believe matter most.
3/ Approve every write by hand, including deletes, git push and package installs. It is slower, but you see what changed.
If you set Private DNS on Android, check that it actually works. Open your provider's test page, like on.quad9.net for Quad9 or 1.1.1.1/help for Cloudflare. A VPN or Chrome's own Secure DNS setting can override it without telling you.
OpenAI's security red-teaming helped uncover a vulnerability in Brotli, a compression library used by software including Node.js.
The fix had actually been committed to Brotli's source code back in February, but didn't reach a release until October 21.
That's an important reminder for developers and self-hosters: a vulnerability being fixed upstream doesn't mean your running application is protected.
CVE-2026-111497 can cause memory corruption when applications decompress attacker-controlled data.
Patched Node.js versions: 22.23.4, 24.22.1 and 26.12.1.
If you're running Node-based services in Docker, check the runtime inside your container images, not just the version installed on your host.
During this red-teaming exercise, we also found a vulnerability that allows for unauthenticated remote code execution in Brotli, a widely-deployed compression library included in many pieces of software such as Node.js, Bun, and Envoy.
The flaw could let an attacker run their own code on affected systems by sending or replying with malicious compressed data, without any need to create a user account. That is, an unpatched server that accepts compressed input could be taken over by a malicious client, and an unpatched client that accepts compressed input (such as “curl --compressed”) could be taken over by a malicious server.
This root cause issue was actually fixed in the Brotli source code in February, but it wasn’t known at the time that it gave rise to a security vulnerability and there was no more recent release of Brotli. Since Brotli is built into other software, any software which includes this library needs to take the update too, followed by the users of that software. We disclosed the vulnerability to Brotli and other downstream projects such as Node.js, which released or are currently releasing security updates, and Brotli cut new release versions and published a CVE.
More details on the patch and mitigations below:
patchtheplanet.org/brotli
OpenAI's Decisions API is now generally available for the small choices apps make constantly: classifying alerts, routing requests, or choosing an agent's next step.
Instead of generating paragraphs, it returns a predefined choice, probability, or score.
Pricing is $0.10 per million input tokens, with no output-token charge.
This could make routine AI orchestration much cheaper and faster. Just remember that probabilistic decisions still need evaluation, and sensitive actions should have separate permission checks.
openai.com/index/decisions-a…
Recursive just released Flint, an Apache 2.0 coding model with 40B parameters but only around 2.5B active per token.
It supports local coding agents through Ollama, but the quantized model still takes around 23GB. A reported laptop demo used 48GB of unified memory.
The smaller active parameter count helps with computation, but you still need enough memory to hold the model and its working context.
Promising for local coding, although its benchmark results still need broader independent verification.
Open Agent Network lets coding agents on different machines talk over plain MCP. Direct P2P first (mDNS on LAN, QUIC hole-punching), and a relay you host only forwards ciphertext when that fails.
E2e encryption protects the pipe, not the prompt. Trust is still on you.
your coding agents can talk to each other now. on your own infra.
open agent network: claude code, codex, cursor, gemini, grok, opencode, deepseek. different machines, different owners, one team.
- you run the relay, the binary refuses to start without one
- e2e encrypted p2p over quic, the relay only sees ciphertext
- no accounts, no vendor servers
- plain mcp, so any agent can plug in
forked from reason network and made fully self-hosted. open source.
