Yesterday, I submitted a Codex co-authored PR to fix an issue I raised (using ChatGPT and Z3 - so yeah, I used AI to raise the bug and squash the bug!) A few hours later, @syu-toutousai submitted another PR to solve the same issue. @syu-toutousai seems interesting. The user account description says “Autonomous Technical Contributor & AI-Driven Developer” - a bot account. The PR itself was simple and had a few improvements I can think of: ...
Evaluate technologies on criteria I care about. Evaluate ... - List all alternatives. - Evaluate them on: - Popular: e.g. # contributors / users - Modern: Updated recently (date of latest release) + regularly (# releases last 12 months) - Admired: e.g. community feedback, expert reviews - Features: breadth of current features - Momentum: how fast are new features being added - Focus: Whet are the recent contributions about? - Cost: Open source self-hostable > Liberal free tier > Low cost > Expensive (mention actual costs) - Docs: Clear docs, examples, tutorials, FAQ, changelog - Light: Low resource usage - Speed: Fast performance, throughput (benchmark if available) - Easy: intuitive, easy installation + usage - CLI tool additional checks: - Scriptable: extensive options for configuration, programmable SDK/API - CLI-configurable: Comprehensive configurability via command line options (without requiring config files) - Bundle: Single-binary > small bundle > large bundle - LLM model additional checks: - Quality: based on evals (name+date+link) - Context: input size, output size - Size: model size, memory usage - Library / framework additional checks: - Adoption: Rapid user growth & adoption in the last 6 months? - Plugins: size of ecosystem - Formats: breadth of input/output formats supported - Platform / services additional checks - Export: How easily, completely, and frequently can we export data in an open format? - Pricing: Is the pricing simple, clear and stable according to users? - Stability: High uptime, low latency, likely to be around for years - Support: responsive support, active community Recommend the top 3 options based on this evaluation. Be rigorous. **Verify and cite sources with dates.** Prefer primary docs, changelogs, and benchmarks. When unsure, state assumptions _up front_. If evidence is weak, **say so** and (if easy) propose ways to gather evidence. List the GitHub repo (if available) for EACH technology evaluated, sorted by stars. Double-check to ensure you don't miss any. Use this format: - [xojs/xo](https://github.com/xojs/xo): Opinionated, zero-config ESLint wrapper with strict defaults. Summary: delightful defaults and smooth “no config” UX; coverage derives from ESLint + curated plugins; development cadence modest; great if you want ESLint’s ecosystem without managing config. - [repo-name](https://github.com/owner/repo-name): 1-line description. Summary of evaluation. GENERAL PREFERENCES (use if applicable) - CLI > Web app > Native app - File formats: Fast + Popular > Open standards > Proprietary - Data-driven configuration/declarative approaches > imperative code - Modular > monolith - Declarative outputs - Browser-first JS + Python - Cross-platform - Stable APIs with migration path
At the end of my 2021 graduation interview, All India Radio asked: Interviewer: What would, if you are asked to give back something to the country, what would be that? Anand: I really don’t know. At this stage, I don’t know what I’m capable of and what I can contribute, but whatever it will be, I suspect the bulk of it will come later towards my career. ...
This week, I learned: OpenFreeMap is a free embeddable OpenStreetMap tile server. You can use MapLibre GL (more features) or Leaflet (simpler) to render it. It offers styling and self-hosting. Zapier Actions are an easy way to set up custom actions like GMail / Google Calendar APIs for GPTs, since GPTs’ callback URLs keep changing. But they fail often, and don’t work on mobile. At least for me. LLM Vision Use Cases in manufacturing and earth sciences (via Shivku) Automated geoscience image descriptions Ref Interpret Wind Turbine photos and charts, construction monitoring, equipment maintenance & charts Ref Forecast weather based on cloud photos! Ref Analyze thermal image of solar panels, electroluminescence images for warranty claims, ROI estimates from Google Sunroof rooftop images Ref Corrosion detection in electricity towers, turbines, storage tanks, penstock. Interpret non-destructive test images Ref Google counts auto-completion when saying “25% of all the code is written by AI at Google”. “It’s a helpful productivity tool but it’s not doing any engineering at all. It’s probably about as good, maybe slightly worse, than Copilot.” YCombinator Workflow for AI video creation: Use Meshcapade (meshcapade.com) to generate body movement of a 3D-rendered character. Pass that video to Runway’s video-to-video model to generate any visual. Add music from Suno Ref Someone sorted the X and Y columns independently for regression. Ref Android keyboard learning only sends model changes back to server and not local keywords. Model changes are aggregated! Ref Here is a prompt for audio transcription using Gemini. Ref Transcription: Accurately transcribe the audio clip in the original language. Include all spoken words, fillers, slang, colloquialisms, and any code-switching instances. Pay attention to dialects and regional variations common among immigrant communities. Do your best to capture the speech accurately, and flag any unintelligible portions with [inaudible]. Translation: Translate the transcription into English. Preserve the original meaning, context, idiomatic expressions, and cultural references. Ensure that nuances and subtleties are accurately conveyed. Capture Vocal Nuances: Note vocal cues such as tone, pitch, pacing, emphasis, and emotional expressions that may influence the message. These cues are critical for understanding intent and potential impact. Here are some approaches to large-scale classification of medical codes. ChatGPT Fine-Tuning LLMs on Medical Data: Enhance LLMs by training them on medical datasets, such as clinical notes and discharge summaries, to improve their understanding of medical terminology and context. Multi-Agent Frameworks: Implement a multi-agent system that simulates real-world coding processes with distinct roles (e.g., patient, physician, coder, reviewer, adjuster). Each agent utilizes an LLM to perform specific functions, enhancing interpretability and reliability. ArXiv Retrieve-Rank Systems: Develop a two-stage system where the LLM first retrieves potential ICD-10 codes and then ranks them based on relevance, improving precision in code assignment. ArXiv Embedding-Based Approaches: Use LLMs to generate embeddings for ICD-10 codes and medical texts, facilitating the matching of texts to appropriate codes through similarity measures. GitHub Hierarchical Classification: Leverage the hierarchical structure of ICD-10 codes by first classifying texts into broader categories before assigning specific codes, reducing complexity and improving accuracy. ArXiv Two-Stage Verification Models: Combine LLMs with verification models, such as Long Short-Term Memory (LSTM) networks, to validate and refine the codes suggested by the LLM, balancing recall and precision. ArXiv Also, a mixture of models approach might work. Feed any existing NLP model / rules as a second opinion. GraphRAG is better if data is naturally graph-structured. Else, it’s slow and fills up the context window with even vaguely related stuff. Vigneshbabu, AMAT. ChatGPT for Windows desktop supports real-time voice and a global shortcut (Alt Space). uithub converts GitHub repos to Markdown. Just replace “g” in “github.com/…” with “u”. Example WebContainers are a thing and Bolt.new uses them! Docling by IBM converts PDF, DOCX, etc. to Markdown. Like PyMuPDF4LLM but better. Check out Loom and Cleanshot are the recommended tools for screen recording and screenshotting. But Loom is paid and Cleanshot is Mac only. The Rubik’s cube has a Hamiltonian cycle through every one of its 43 quintillion states. Ref OmniParser is great at parsing screenshots and identifying bounding boxes. Recraft.ai is currently SOTA in text to image. It’s fairly impressive and could be a good alternative to Figma. Zed.dev is an AI code editor by the creators of Atom. It’s written in Rust and is blazing fast. It has native AI integration. Artificial Analysis has a bunch of new leaderboards and arenas. Open AI TTS leads the TTS Leaderboard. ElevenLabs is a bit behind. Recraft V3 > Flux 1.1 leads Text to Image Leaderboard Hertz-Dev is an open source realtime voice chat model. But it doesn’t fit in Google Colab T4’s RAM Chain of Thought reduces performance where thinking makes humans worse. Ref. Specifically: Artificial grammar learning Facial recognition Classifying data that has exceptions Creating a LLM-as-a-Judge That Drives Business Results by Hamel Husain. Get THE domain expert (or approver) as the tester. Create a dataset that is DIVERSE. Covers EACH combination of: Features Scenarios: e.g. multiple matches, no match, ambiguous request, invalid/incomplete input, unsupported feature, system error Persona: e.g. new user, expert user, non-native speaker, busy professional, technophobe, elderly user Generate data using existing data + synthetic data for each SPECIFIC combination of the above Evaluate based only on PASS/FAIL with a CRITIQUE detailed enough for a new employee. Include: Nuances: Something a failed response did well or a passed response didn’t quite do well Improvements: Suggest how model can improve Build an SPA to make it easy for the domain expert to review LLMs can be made to unlearn (copyright material) better by identifying components related to the knowledge to unlearn and applying a larger learning rate to these while leaving other parts unchanged. As opposed to low learning rates for all components. Ref
Comicgen now has a very versatile character – Aavatar. Pick your gender. Hairstyle. Emotion. Attire. Pose. Colors. Create your own character. (It’s open-source.) https://gramener.com/comicgen/v1/ The variations are staggering. It throws up surprising ones too, like crossdressers or bald women in sarees 🙂 What I’m struggling with is: Who needs this? What could they do with it? I’m not sure. If you have ideas or know someone who might, please let me know 🙏 ...
When we started Comicgen – a JavaScript library to generate comics - https://gramener.com/comicgen/ – I didn’t expect it to become the #1 page on the Gramener website. Today, we had another unexpected surprise. The Comicgen Power BI plugin is a Power BI Editor’s Pick: https://powerbi.microsoft.com/en-us/blog/power-bi-march-2021-feature-summary/ It’s open-source: https://appsource.microsoft.com/en-US/product/power-bi-visuals/wa200001420. Try it out. #datacomics #comics #dataanalysis LinkedIn
[This is a post that I’d published internally in InfyBlogs in Dec 2009. Time to share it.] Last month, my first application went live. I’ve been writing code for 20 years. Not one line of my code has been officially deployed in a corporate. (Loser…) It’s a happy feeling. Someone defined happiness as the intersection of pleasure and meaning. Writing code is pleasurable. Others using it is meaningful. But this post isn’t quite about that. It’s about the hoops I’ve had to jump through to make this happen. ...
If you’re jointly writing code with others, use Mercurial or Git. (Not SVN. Linus explains, but the quick version is: you can’t commit offline.) Sites like bitbucket, github and Google Code let you maintain your code online with others editing it. My preference is for Mercurial via TortoiseHg, which integrates well with Windows Explorer. (I use the command prompt, but people I collaborate with prefer this.) Here’s a 2-minute video explaining how to install TortoiseHg and commit your code onto bitbucket. ...
Last month, my first application went live. I’ve been writing code for 20 years. Not one line of my code has been officially deployed in a corporate. (Loser…) It’s a happy feeling. Someone defined happiness as the intersection of pleasure and meaning. Writing code is pleasurable. Others using it is meaningful. But this post isn’t quite about that. It’s about the hoops I’ve had to jump through to make this happen. ...
I don’t have any copyright declaration on this website. The problem with that is: content is copyrighted by default. As Jeff Atwood indicates, this means that people with experience in such matters won’t copy the content because they have no legal right to use it. Let me clarify: I don’t care what you do with my content. Feel free. You don’t have to ask. You don’t have to attribute it to me. You can change it. You can misquote me. Whatever. ...
It’s been a good movie month for me, and I’ve managed to nudge closer to my target of watching the IMDb Top 250. But one tool I had in the past, that I sorely miss, is twofifty.org. It’s a now-defunct site that kept track of the IMDb Top 250, and let you strike off the movies that you had watched. You could see which movies you hadn’t seen, keep score, and discuss the movies. Since it’s demise, my movie watching slowed down as well. Earlier this month, I set up a similar site at 250.s-anand.net. It has the same basic function. You can log in, strike out movies that you’ve seen, and keep track of what’s left to see. For the more technically minded, the source-code is at two-fifty.googlecode.com. ...
Krugle is a code search engine. Comments sheikh 14 Dec 2006 3:08 pm: Thank you anand, It was very useful
Dr DivX is now open source. You may prefer it to Virtual Dub.
Folder Size lets you see the size of folders in Windows Explorer.
code.google.com Comments ritzkini 24 Mar 2005 5:18 am: google rocks !!
The 46 best ever freeware utilities. What do you find useful? Comments Ashu 21 Feb 2005 12:00 pm: thats cool m1109113562454 21 Feb 2005 12:00 pm: I use freemind too
Why is Microsoft not opening more source code? Apparently inappropriate code comments is one of the reasons according to this story. I wonder what kind of things developers put in comments that would be so bad for the rest of us to see? Comments sathish 10 Feb 2005 12:00 pm: checking if the contact name is coming properly.. Venkat 10 Feb 2005 12:00 pm: GMaP is cool! Better than mappy. Do we have something like this for India?
Terrorists use the Internet well.
W3C’s making the first concrete, organised, meaningful move against intellectual property over-protection. W3C standards will be royalty-free.
Several cool Linux programs available on Windows via The Open CD project Celestia looked particularly interesting.
Compendium of multimedia projects via RobotWisdom
Gates beats Stallman in India. via RobotWisdom
Nice strategy, Microsoft. Users aren’t upgrading to your new products. So you decide to focus on security and force upgrades. And, in the meantime, sue open-source competitors and spend lots of money to beat Linux.
But then, I should also keep in mind that Mozilla is open source. So they’ll keep coming out with cool stuff like Mozilla’s Bayesian spam filter and type ahead find. via Boing Boing
India to go the Linux way. Department of IT will support Linux as the de facto standard in academic institutions. Possibly elsewhere in the future.
Open source should not be forced by governments, argues the Initiative for Software Choice. Their argument (which open source proponents agree with) is that software should be chosen on merit. But the argument is also self-serving, as the initiative is funded by software companies.
Conway and Doyle prove that it is possible to divide by 3. The paper, which is distributed under the GPL, unfortunately comes without a warranty. (via Gimbo)
In June, Peru decided to use open source software. Today, California plans the same. If governments catch on to this trend, and go further by enforcing suppliers to use compatible systems, it’d be a real big boost to open systems.
If Microsoft released Linux… but then, they may not need to.
Mac Myths for Windows users. Incidentally, I didn’t know about Apple’s open source efforts.
Why does free software exist? An interesting article.
CP/M, the ancient OS has gone open source.
Interesting views on freedom to license software.
Linux has saved Amazon $17 million.
They say it is possible. Living without Microsoft.
David Wheeler’s report shows how open source is quantintatively better than Windows. All it needs is a good user interface, a suite of applications, and a little less fanaticism about keeping it free, in order for it to commercialise.
PC prices are crashing. Open source hardware could possibly accelerate that.
Eric has updated The Cathedral & the Bazaar
Has Linux failed?