标签：#discuss

You heard me. Alright, that was mean lol. Though based on the title, you probably already knew the...

Every programmer wants to improve. We all dream about becoming the person who can look at a...

"our work got checked by an external reviewer." That's what Fable said after I brought Gemini...

I recently learned something about building products that I probably should have understood much earlier: People liking your product doesn't necessarily mean they need it. I built a platform called Rizzzler, an open-source profile/link-in-bio platform. The idea was pretty simple. I'd seen people using platforms where they could put a link in their social media bio and create a small personal page. I thought I could build my own version — something simple, fast, customizable, and a little more fun. So I built it. And because I wanted people to be able to trust what they were using, I made the project open source too. I spent a lot of time building the actual product. There are profiles, customization, coins, notifications, milestones, community chat, and other small systems intended to make the platform feel less like a static link page and more like something people could actually interact with. At that point, I thought: "Okay, now I just need people to find it." That turned out to be the easy part. Then I started promoting it. I submitted Rizzzler to places like Product Hunt, SaaSFrame, and other platforms where people discover new products. And for a few days, things actually looked pretty good. I started getting visitors. At one point, the traffic was above the 25th percentile for the category I was looking at in GA4. People were visiting. Some people signed up. And I started getting feedback like: "Good UI." "This is good." "Someone finally made link-in-bio profiles look cool." Those comments felt great. They also gave me a slightly dangerous impression: Maybe I've built something people actually want. Then the traffic stopped. Not gradually. It just became cold again. The initial spike from launching and posting about the product disappeared, and there wasn't enough organic interest to keep bringing people back. That was the part I didn't expect. The product wasn't necessarily bad. This is something I've been thinking about a lot. I don't think the main problem

We’ve all been there: staring at a delicious plate of pasta, trying to figure out if it's 400 or 800 calories. Manual tracking is a chore, and standard apps often fail at portion estimation. But what if we could combine Computer Vision , Multimodal LLMs , and Vector Databases to build an automated nutritionist? In this tutorial, we are building a state-of-the-art Multimodal Food Estimation Pipeline . By leveraging the Segment Anything Model (SAM) for precise boundary detection and GPT-4o Vision for contextual analysis, we can bridge the gap between "looking at a photo" and "calculating nutritional density." Whether you're interested in AI-driven wellness , FastAPI development , or Multimodal RAG , this guide covers the full stack. The Architecture 🏗️ The pipeline follows a sophisticated "Identify -> Analyze -> Match" flow. We don't just ask GPT-4o "what is this?"; we use SAM to isolate food items first to ensure the LLM focuses on the right pixels. graph TD A[User Uploads Image] --> B{SAM Model} B -->|Segmentation| C[Isolated Food Patches] C --> D[GPT-4o Vision API] D -->|Item + Volume Est.| E[Embedding Generation] E --> F[PostgreSQL + pgvector] F -->|RAG Retrieval| G[Verified Nutritional Data] G --> H[Final Response: Calories & Macros] Prerequisites 🛠️ Before we dive in, make sure you have the following ready: Python 3.10+ OpenAI API Key (for GPT-4o) PyTorch (for SAM) PostgreSQL with the pgvector extension enabled FastAPI for the backend Step 1: Precise Segmentation with SAM 🎯 The biggest challenge in food AI is overlapping items. Using Meta’s Segment Anything Model (SAM) , we can extract the exact mask of a food item, which helps in calculating the relative "area" occupied on the plate. import torch from segment_anything import sam_model_registry , SamPredictor import cv2 # Load SAM model sam_checkpoint = " sam_vit_h_4b8939.pth " model_type = " vit_h " sam = sam_model_registry [ model_type ]( checkpoint = sam_checkpoint ) predictor = SamPredictor ( sam ) def get_f

Intro AI Avatar is a free app where your VRoid (VRM) avatar cheers you with all its might .🤗 It lives in your VS Code sidebar (reacts to Claude Code / GitHub Copilot) or browser side panel (reacts to ChatGPT / Claude). Animations and speech bubbles all run without AI too. This time I have three main topics. 🤝Catbot Integration 🏢AI Office 😺Cat Mode Let's see how they are! Catbot Integration I was asked to collaborate with my DEV Community friend @annavi11arrea1 Catbot . Catbot is A galactic robot cat you can talk to from any device — and a harness that lets you switch between (or combine) all of your AI models. https://github.com/AnnaVi11arrea1/catbot I was happy about this offer because I loved Anna's creativity and cool designs. I added the features below to AI Avatar to integrate Catbot. Launch Cat button: With this button, AI Avatar can run Catbot. Catbot with button: This makes Catbot stay beside AI Avatar. Cat Boss button: This changes the AI Office boss from a VRM avatar to Catbot. Cat Mode Many people feel that animals are healing and soothing. It is close to the AI Avatar concept of cheering people up. So I decided to add Cat Mode . I added the features below to make it look like a cat. Cat-like text, "Meow/Purrr" in English and "にゃ～" in Japanese Cat emojis Cat pose animations A new avatar with cat ears and cat whiskers. To tell the truth, the hardest part of making this mode was adding whiskers to the avatar using Blender . I can do basic things in Blender, but it is too difficult for me, even with the help of AI, just to add whiskers. It would be more fun if I added other animal modes too. AI Office AI Avatar displayed only one avatar. I thought it could do more things if it displayed several avatars at once. So I added AI Office mode. Two avatars are displayed and talk and move around when idle, and they also make a communication animation when using AI or clicking. I made one avatar a boss and one a worker. The hard part of making this mode was the timin

When many people are first learning how to code, they find it difficult and when they ask, "How can I get better at coding?" they are usually told, "With time and practise it will get easier." . But instead of using so much time and effort to get better at coding using hard programming languages, what if coding could get better for you instead of you getting better at coding ? Well, this is the reason that inspired me to make a new programming language called Sofya . Sofya is designed to be so simple (even simpler than Python ) so that anyone can find programming easy and fun. But to prove my point, let us use an example. Let us say that we want to make a program that will show us all the numbers from 1 to 20 . Let us compare how this program will look like in Python and Sofya . The Python Program for number in range ( 1 , 21 ): print ( number ) The Sofya Program Variable Number is 0 Do this { Increase Variable[Number] by 1 Write Variable[Number] on the screen } Until Variable[Number] = 20 From this example, we can see that the Sofya program is easier than the Python program, for a beginner in programming, for the following reasons: Sofya uses simpler commands than Python: It is easier for a beginner in programming to remember the command Do this...Until Variable[Number] = 20 , which is used for making a loop, as compared to the command for number in range(1, 21): . Sofya's syntax is closer to English as compared to Python's syntax: When we are making a loop variable in Sofya, we simply say Variable Number is 0 rather than saying number in range(1, 21) in Python. The Sofya program can easily be understood by anyone even if it is the first time that they are seeing it as compared to Python: A beginner in programming can easily tell that in the line where we say Increase Variable[Number] by 1 , that we are increasing the value of the variable called 'Number' by 1 as compared to the line number in range(1, 21) in Python. If you would like to try out Sofya for yourself

In mid-July, my Google clicks in my home market (Israel) dropped by almost half. Buyer-intent queries that used to bring steady leads just evaporated from Search Console. While I was staring at GSC dashboards trying to figure out what broke, I finally did the thing I should have done months earlier: I stopped looking at dashboards and started reading raw server logs. What I found there was a parallel universe. Google Search was sending me less than ever — but AI systems were reading my site constantly . Not "someday this will matter" constantly. Right-now constantly: an AI assistant was fetching a page of mine roughly every 26 minutes, around the clock, because a real human had just asked it a question. So I built a small log analyzer and let it run. Here's what 34 days of complete Caddy logs from a small business site (about 70 real human visitors a day) actually look like. The numbers All counts are HTTP 200 responses only (more on why below), over 34 days: Bot Requests Per day What it is bingbot 5,444 158.2 Bing's index — which feeds ChatGPT ChatGPT-User 1,388 40.3 Live fetch while a human asks ChatGPT Googlebot 1,233 35.8 Classic Google crawl GPTBot 547 15.9 OpenAI training crawler Claude-User 519 15.1 Live fetch while a human asks Claude OAI-SearchBot 281 8.2 ChatGPT search indexing Applebot 268 7.8 Apple (Siri / Apple Intelligence) ClaudeBot 214 6.2 Anthropic training crawler Amazonbot 136 4.0 Amazon (Alexa & co.) PerplexityBot 103 3.0 Perplexity indexing Three things in that table genuinely surprised me. ChatGPT-User outreads Googlebot. 40.3 fetches a day versus 35.8. This isn't a crawler building an index for later — ChatGPT-User is the user-agent OpenAI sends when a human is mid-conversation and ChatGPT decides to pull a live page to answer them. On my site, that now happens more often than Googlebot visits. For a tiny business site in a niche market, I did not expect that. Bing crawls 4.4x harder than Google. 158 requests a day versus 36. Nobody optimizes

A known-bad regex is useful evidence, but putting it directly in the test process can hang the runner before the timeout assertion fires. The boundary I am using: run each adversarial case in a fresh worker thread or child process let the parent own a hard timeout and terminate the child keep semantic-parity fixtures separate from timing guards require the safer replacement to pass both suites record the timeout class and bounded elapsed time as evidence Browser workers have the same trap: startup time should not consume the execution budget, and output limits matter alongside time limits. Disclosure: I maintain MonoTools. I recently tightened its browser-local Regex Tester around a 300 ms post-startup Worker budget, named groups, replacement previews, and regression cases: try the bounded tester What does your team treat as a deterministic CI failure receipt for ReDoS: an exit code, a timeout class, an elapsed-time range, or something else?

Hey everyone! 🌸 So, recently I was thinking about something and thought I’d share it with you all. 😄...

Anthropic signed the EU AI Act's Code of Practice on Transparency of AI-Generated Content, and...

TL;DR Welcome back to Dev Opportunity Radar. This is a weekly series where I share opportunities,...

Bloomberg reported this morning, August 13, that Anthropic is in talks to buy Decart AI for around $6 billion. Talks, not a signed deal. That distinction matters and I will come back to it. What caught my attention is not the number. It is where Decart came from. The Minecraft thing Decart got famous for Oasis: a playable Minecraft-looking world that no game engine was rendering. The model predicted every next frame based on what you pressed on the keyboard. 20 FPS, interactive, no scene graph, no collision system, no assets. Just a model hallucinating a consistent world fast enough that your hands believed it. In late 2024 that read as an impressive demo with no obvious business behind it. The company was founded in 2023. It has raised over $450M, was valued at $3.1B before this year's round, and its current research page describes three product lines: Oasis , a world model, now explicitly positioned for physical AI and robotics rather than gaming Lucy , a real-time video model running live at 30 FPS DOS , the Decart Optimization Stack: hardware-aware model design, custom kernels, proprietary compilers, inference optimization The demo was the marketing. DOS is the engineering. The reported reason is not robotics Read the actual reporting carefully. Fortune says a deal would bring Decart's video-simulation and chip-efficiency technology into Anthropic's inference team. Bloomberg's sources point at the same thing: the chip efficiency work could help existing infrastructure absorb more demand. So the sourced story is compute economics. Anthropic is compute constrained, spending enormously on capacity, and DOS is a margin lever that applies to every single Claude request on day one. That is a boring, completely rational reason to spend $6B. It does not need a robotics narrative at all. I still think the robotics reading is in there. Why Two things sit underneath. First, Anthropic held acquisition talks with Physical Intelligence this spring. The Information reported it

Ever since I joined the platform, I wanted to post about a topic I was really passionate about....

24 stories. 24 visits. One counter, same six faces. The Third Cup The AI wave hit, and...

Not a flying drone (though count to think of it, that might work), I mean a drone system tray app,...

Following Anthropic's confirmation that all text generated by its new Claude models will carry an invisible watermark in order to identify that the text has been generated by AI. Read more about this measure at: https://support.claude.com/en/articles/16266773-how-claude-marks-ai-generated-content Today, developer Guillaume Meyer published "watermarks-remover" on GitHub: an open-source project that cleans those signals generated by LLMs, such as Claude, Gemini, OpenAI and others, removing invisible Unicode characters, C2PA metadata and more. 🔗 Repository link: https://github.com/guillaumemeyer/watermarks-remover

used to have a habit of thinking in code. it'd be like walking down the street and immediately seeing...

The people who make open source work aren't just the ones writing code. Some of them write the words that make the code make sense. I spent years assuming open source was a closed door. Every time I opened GitHub, I felt like I'd wandered into a conversation being held in a language I hadn't studied. Pull requests, forks, issues tagged with words like "good first issue" that somehow still felt intimidating. I closed the tab more times than I can count, convinced that space belonged to people who could write functions, not people who could write sentences. It took me longer than I'd like to admit to realize how wrong that assumption was. The myth that keeps people out Open source has a branding problem, and it's an ironic one for a movement built on collaboration. The public image is almost entirely code: commits, merges, terminals, lines of syntax scrolling past on a dark screen. That image is accurate, but it's incomplete. It leaves out the writers who make a tool's documentation actually usable. It leaves out the designers who turn a clunky interface into something people want to use. It leaves out the community managers who keep a project from imploding when a disagreement gets heated. It leaves out the translators, the testers, the people who write the first draft of a README at 11pm because nobody else got around to it. If you've stayed away from open source because you don't code, you've been kept out by a myth, not a rule. What non-developers actually do in these projects Documentation is the most obvious entry point, and it's also one of the most needed. A huge number of open source projects are built by people who are excellent engineers and mediocre explainers. That's not a criticism, it's just a different skill. Someone can write brilliant code and still produce a setup guide that only makes sense to the person who wrote it. Projects need people who can sit with a piece of software as a genuine beginner would, notice where the instructions fall apart, and

My hobby🍧 My first and absolute favorite hobby is travelling around the world. 🌍✈️ I love visiting...