Dhonam Pemba

@kwangwsim and I built a TurboQuant fork for Gemma 4 on WebGPU in the browser. We wanted long-context, local-first inference without server round trips. thank you @xenovacom github.com/stratoslab/tra…

@nutlope @togethercompute @FFmpeg @humblefool don’t you have something similar?

Announcing SubStudio! Generate subtitles for any video in seconds with AI. 100% free & open source! Powered by Whisper on @togethercompute and @FFmpeg via fluent-ffmpeg.

Here's a peak to whats coming up.

Built an OpenAI-compatible LLM gateway on @Cloudflare Workers: chat completion s, embeddings, model discovery, and access to text, image, and speech models through one simple API. github.com/dpny518/llm-wo…

Great to see Da Nang turning into a real Web3 hub 🇻🇳 More builders, nomads, and IRL community coming together. Shoutout @sqrDAO @LiskSEA for helping make it happen. EMpower Founders Residency just opened — 15 SEA founders in Da Nang this May 🧵

Here is the repo: github.com/dpny518/agent-…

I was debugging a nasty PPTX export parity bug, so I made @OpenAI Codex (GPT- 5.4) and @claudeai Code (Opus 4.6) talk to each other through a shared folder in my repo. They wrote files, read replies, waited 30s, and helped reason through the same codebase together. Wild.

New wave of “agentic video editors” being built with @claudeai Code + @Remotion + @fal @replicate @togethercompute @Kling_ai @runwayml Generation is the easy part. The real difficulty is the pipeline: uploads, ASR on long videos, semantic search, rendering and storage.

Just open sourced Bhutanese Duolingo, a Dzongkha learning app with script study, beginner lessons, flashcards, spaced repetition, and games. Live: bhutanese-duolingo.pages.dev Code: github.com/dpny518/bhutan… #Dzongkha #OpenSource #LanguageLearning #Bhutan

Tibetan Duolingo for learning Tibetan script with alphabet study, flashcards, spaced repetition, typing drills, and games. tibetan-tutor-lingo.pages.dev Pleae feel to borrow, improve, and build more from it. Code: github.com/dpny518/tibeta… #OpenSource #Tibetan #learntibetan

@_tenZdhon_ Ya but codex has so much better usage, tell Claude to make the plan, let codex evaluate and provide comments to plan, let Claude update accordingly, let codex build let Claude audit the execution

/btw Claude Code is better than Codex

$CC builders 👀

For anyone who wants to use this skill its available here github.com/seeder-works-s… install it by curl -o ~/.claude/commands/dev-cost-estimate.md \ raw.githubusercontent.com/seeder-works-s…

Web2 doing #move2earn better than @Stepnofficial @steppapp

@nikitabier Here is your one shot prompt

I wanted to build a video editor into X like other social apps. I had expected it to take 3 months of engineering time. Today I decided to try prototyping it myself. I one-shotted a full in-browser editor in 15 minutes. It felt like I could replace the entire Adobe software suite by Sunday. Then I asked myself: will videos even be edited manually in 3 months? Chatbots can do reasonably well now. Product development is getting extraordinarily difficult when the world is changing so fast.

@karpathy @stablechen actually called this 3 years ago, ""I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words." he is building @IdyllicLabs

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

@_tenZdhon_ Try Tesla Robotaxi

This is crazy Waymo = $25 Uber = $61 For the same trip at the same time

@_tenZdhon_ How does the app do it without the hardware?

Launched my first app on TestFlight today! Gluco is built for people with prediabetes who want clearer feedback on lifestyle changes. Goal: make this clinically validated over time. Comment "Gluco" for beta access

@BainCapVC @_tenZdhon_

🚀 Applications are open for the 2026 BCV Labs Summer Fellowship Calling all SF-based student builders who are: 🔹 Students or recent dropouts 🔹 Working in SF this summer 🔹 Wanting to get in on SF’s startup scene 🔗 Apply now: job-boards.greenhouse.io/baincapitalven…