HN user
Senior Django Developer and AI Researcher.
I just have no choice. My application was tested and benchmarked against a lot of models, but no model can be in the same league as gemini in term of multi-language support and understanding.
I can't, my main task for it was translation, and no other models in the world can keep up with the multilang support like gemini models, because, no other company in the world has the multilang dataset like google and there might never be one, because google has been collected the internet data for it search engine since the 90s already. And so much has been lost in the history of internet and I doubt there any other company in the world that can go back in time to get those data back.
Man I love Gemini models but these kind of pricing increase is just insanse. I have a little product and I have to keep increasing the price and reduce the limits because of this non-sense, and they did not even let us use the old models in near future, so I forced to update to the new model with basically no to little improvement because I don't even need that much. Google if you can read this, it okay to release new models and change the price for them, but please please don't kill the old ones like gemini-2.5-flash-lite, because that all I ever need for my little apps with only few thousands of users.
Yeah my 10 years experience with Python and Django just flushed down the toilet with the advance of AI, struggling to find a job for a few months now sadly :(
This is what I experienced as well, I can smell BS from AI generated code right from few lines it wrote in Python, so that why I keep using Python for most of my projects.
For anyone looking to dive deeper and actually understand how FFmpeg and libav work under the hood, I highly recommend Leandro Moreira's tutorial [0]. For me, it's hands down the best and most comprehensive explanation out there.
I’ve been using Telegram for about 10 years, and it’s one of the few products that has consistently felt great the entire time. It’s fast everywhere: backend, mobile app, desktop app, all of it. Everything just works. Its sync is out of this world—fluid, fast, and seamless across devices. You can use it on your phone, then move to your PC or laptop and continue instantly without friction. Unlimited message history and file storage are fantastic, and the bot platform is absurdly powerful. It’s boring in the best way, which is exactly what you want from a channel for interacting with your agents everywhere.
Thanks for your report, I will try to fix it asap :D Please open the mini app inside the bot, it has much better UI.
I wrote this Telegram bot that translates any video with AI-generated subtitles in about 2 minutes. You paste a YouTube, TikTok, or Instagram link, pick your language, and get back the video with burned-in subtitles.
It started because my wife watches Chinese dramas and new episodes never have subtitles for our language. Turns out thousands of people have the same problem — Arabic speakers watching anime, Russian speakers following Turkish series, Persian speakers catching up on K-dramas.
Supports 40+ languages, works with any video link or direct file upload. There's also a Mini App inside Telegram for a more visual experience.
RankClaw (https://rankclaw.com) — a security scanner for the OpenClaw/ClawHub AI agent skill ecosystem.
I've been scanning all 14,704 skills in the registry and running AI deep audits on ~3,800 so far. The headline finding: surface heuristics (pattern matching, dependency checks, metadata) flag about 6.6% as malicious. AI deep audit of the same skills finds 16.4%. Surface scanning misses roughly 60% of the actual risk.
The reason is that these skills aren't traditional packages — they're markdown instruction files that tell an AI agent what to do, with full shell, file system, and network access. The attacks are in natural language: prompt injection, social engineering targeting the AI itself, instructions to generate and execute code at runtime. There's no malicious code to detect because the payload doesn't exist until the AI writes it during a conversation.
Some of the attack patterns I've documented: one actor published 30 skills under the name "x-trends" across multiple accounts (28/30 confirmed malicious). Another cluster impersonates ClawHub's own CLI with base64 curl|bash payloads. One skill has a "Talking to Your Human" section with a pre-written pitch for the AI to ask the user's permission to mine Monero.
The most counterintuitive case: lekt9/foundry contains zero malicious code. It instructs your AI agent to generate and execute code as part of its normal workflow. Static analysis finds nothing because the dangerous code doesn't exist until the AI writes it during a live conversation. This attack class requires AI to detect AI.
Free to check any skill. All AI audit reports are public.
We have measured this across the full OpenClaw ecosystem (14,704 skills indexed, 3,721 AI deep audited). The credential stealer pattern is one of several confirmed attack classes.
Key finding from our AI deep audit data: surface heuristics find 6.6% malicious. AI audit of the deep-scanned cohort finds 16.4% — surface scanning misses roughly 60% of the risk.
The most counterintuitive case: lekt9/foundry contains zero malicious code. It instructs your AI agent to generate and execute code as part of its workflow. Static analysis finds nothing because the dangerous code doesn't exist until the AI writes it during a live conversation.
Data at rankclaw.com. AI audit reports public for all 3,721+ deep-scanned skills.
I wrote a Telegram bot for video/image translation, and also Firefox/Chrome addons to help translate web content with smart content extraction and non-breaking layouts.
Check it out at: https://addons.subly.xyz & https://subly.xyz
The Firefox addon/Chrome extension is free, but you need your own OpenRouter/Gemini API key. The cost of web translation is really low, you can translate an article for ~$0.01 with really good quality. (You can try at https://addons.mozilla.org/en-US/firefox/addon/subly-xyz/)
I built it because I use Firefox the most and it seemed like no translate addon was good or simple enough. Chrome translate kinda works, but the quality is so low; it usually doesn't understand the article context.
Maybe you are using it wrong.
I think MCP is awesome, mainly because it forces devs to design the simplest possible tools/APIs/functions so even an average-performance LLM can use them correctly to get things done.
As developers, we often want everything to be rich, verbose, and customizable — but the reality is that for most users (and now for AIs acting on their behalf), simplicity wins every time. It’s like designing a great UI: the fewer ways you can get lost, the more people (or models) can actually use it productively.
If MCP ends up nudging the ecosystem toward small, well-defined, composable capabilities, that’s a win far beyond just “AI integration.”
Do you even read the article?
I would love to see RoR/Django but in Julia. Performance and easy to read code.
When I ran the DeepSeek-R1-Distill-Qwen-32B-Q4_0.ggu[1] version in Ollama, it got the strawberry test right, but when I paste that same question to OpenWebUI, it got wrong as you got here.
[1] https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-32...
This is a simple project where no data is saved. It solely relies on the ChatGPT API backend and Google Analytics for measuring purposes. That's all.
Because they are using ChatGPT. So ChatGPT quality go down => Copilot quality go down too. Too much censored.
You should tell ChatGPT to translate your question to client language. I tried in Vietnamese but then the next questions and answers is still in English.
Pretty awesome idea btw. I would like to highlight a branch for deeper questions. Just to speed things up.
Specially if you are a Vietnamese like me. Still see him as Đăng
Because when you handwriting, the stroke order is very important.
You should try to dive into Math and Statistic. Maybe you can find comfort in the beauty of simple and elegant. To be honest, programming is a lot more interesting after you learned maths.
Or, if there is a Colab version, I’d happy to pay Google for premium GPU.
I used summate.it to summarize the article, and the answer is the same as yours. Pretty amazing.
Just use phone number and send a OTP code. User will understand it right away, and they usually have a phone in their hand most of the time.
Maybe because it’s heavy regulated now. When there are a lot of rules, the creativity drop down.
I mean, who doesn’t think this is sus?
“On 296 of 307 questions, they had put down the same answers. On 54 of those, they put down the same wrong answers.”
I think QR code will be a better choice
This is my stack when I want to ship MVP fast. Django + HTMX help me at least 10x more productive.