Indie maker, developer, designer, entrepreneur. Join my free newsletter for the good stuff: https://xitter.cf/t.co/zlU0ohGL0m
Book a Call →
Joined April 2018
- Tweets324
- Following1.4K
- Followers114
- Likes3.9K
David Porkka retweeted
Turned my laptop screen into a window. 🪟
The webcam tracks my head position via MediaPipe, and the @PlayCanvas Engine renders a 3D Gaussian splat with an off-axis projection - so her gun barrel seems to pop out from the screen. 🔫
Splat by @dymensium.
David Porkka retweeted
I made a captcha for humans so only robots can use my website.
In my testing so far 100% of robots passed the challenge and 100% of humans failed.
castrio.me/im-a-robot
David Porkka retweeted
Just off stage at #GoogleIO, some highlights from this morning 🧵
Gemini 3.5 Flash is available today for everyone in @antigravity and across our products and APIs.
Compared to 3.1 Pro, 3.5 Flash is better across almost all benchmarks with huge progress in coding. It’s also comparable to the best models but very fast (4x faster tokens/ second than other frontier models). And when looking at the intelligence versus output speed, it’s in a league of its own in the top right quadrant.
David Porkka retweeted
🇨🇳In Shenzhen China, food glides into your table mid-air, guided by AI.
Delivery pods use magnetic levitation, AI routing, and linear motors for smooth, wheel-free motion. Each pod maps the space, avoids collisions, and optimizes routes in real time
David Porkka retweeted
Starting today, agents can now be Cloudflare customers. They can create a Cloudflare account, start a paid subscription, register a domain, and get back an API token to deploy code right away. cfl.re/4sY0Uxn
I built a cyberpunk-themed personal website that shares my journey from biologist to developer.
It includes an interactive terminal, knowledge graph, and more, all built with @zocomputer.
Check it out at davidporkka.com or view my recording below.
#zocomputerchallenge
David Porkka retweeted
🚨Breaking: Someone open sourced a knowledge graph engine for your codebase and it's terrifying how good it is.
It's called GitNexus. And it's not a documentation tool.
It's a full code intelligence layer that maps every dependency, call chain, and execution flow in your repo -- then plugs directly into Claude Code, Cursor, and Windsurf via MCP.
Here's what this thing does autonomously:
→ Indexes your entire codebase into a graph with Tree-sitter AST parsing
→ Maps every function call, import, class inheritance, and interface
→ Groups related code into functional clusters with cohesion scores
→ Traces execution flows from entry points through full call chains
→ Runs blast radius analysis before you change a single line
→ Detects which processes break when you touch a specific function
→ Renames symbols across 5+ files in one coordinated operation
→ Generates a full codebase wiki from the knowledge graph automatically
Here's the wildest part:
Your AI agent edits UserService.validate().
It doesn't know 47 functions depend on its return type.
Breaking changes ship.
GitNexus pre-computes the entire dependency structure at index time -- so when Claude Code asks "what depends on this?", it gets a complete answer in 1 query instead of 10.
Smaller models get full architectural clarity. Even GPT-4o-mini stops breaking call chains.
One command to set it up:
`npx gitnexus analyze`
That's it. MCP registers automatically. Claude Code hooks install themselves.
Your AI agent has been coding blind. This fixes that.
9.4K GitHub stars. 1.2K forks. Already trending.
100% Open Source.
(Link in the comments)
David Porkka retweeted
It's 3dsvg (3dsvg.design). Free open-source browser tool that turns SVGs, text, or pixel art into interactive 3D objects you can spin, animate, and embed—no uploads or accounts needed. Matches the video exactly.
David Porkka retweeted
10 GitHub repos to spend 60-90% less tokens in Claude Code:
1. RTK (Rust Token Killer)
CLI proxy that filters terminal output before it hits your context
- 60-90% reduction on common dev commands
- one binary, zero dependencies
- works with Claude Code, Cursor, Copilot
Repo: github.com/rtk-ai/rtk
2. Context Mode
Sandboxes raw tool output into SQLite instead of dumping it into context
- 98% context reduction on Playwright, GitHub, logs
- only clean summaries enter your conversation
- works as Claude Code plugin
Repo: github.com/mksglu/context-mo…
3. code-review-graph
Local knowledge graph that maps your codebase with Tree-sitter
- Claude reads only what matters, not the entire repo
- 49x token reduction on large monorepos
- 6.8x on average reviews
Repo: github.com/tirth8205/code-re…
4. Token Savior
MCP server that navigates code by symbols, not full files
- 97% reduction on code navigation
- persistent memory across sessions
- 69 tools, zero external deps
Repo: github.com/Mibayy/token-savi…
5. Caveman Claude
makes Claude talk like a caveman to cut output tokens
- 65-75% output reduction
- one-line install
- keeps full technical accuracy
Repo: github.com/JuliusBrussee/cav…
6. claude-token-efficient
one CLAUDE.md file that keeps responses terse
- drop-in, no code changes
- reduces output verbosity on heavy workflows
- best for output-heavy sessions
Repo: github.com/drona23/claude-to…
7. token-optimizer-mcp
MCP server with caching, compression, and smart tool intelligence
- 95%+ token reduction through intelligent caching
- compresses repeated tool outputs
Repo: github.com/ooples/token-opti…
8. claude-token-optimizer
reusable setup prompts for optimizing any project
- 90% token savings in 5 minutes
- reduces doc token usage from 11K to 1.3K
Repo: github.com/nadimtuhin/claude…
9. token-optimizer
finds ghost tokens that silently eat your context
- survives compaction without losing quality
- fixes context quality decay
Repo: github.com/alexgreensh/token…
10. claude-context (by Zilliz)
code search MCP that makes your entire codebase the context
- ~40% reduction with equivalent retrieval quality
- hybrid BM25 + dense vector search
Repo: github.com/zilliztech/claude…
[ how to stack them ]:
you don't need all 10. pick 2-3 based on your workflow:
> heavy terminal output? RTK
> big codebase? code-review-graph + Token Savior
> lots of MCP servers? Context Mode
> quick fix? Caveman + claude-token-efficient
most people are burning tokens without knowing it
run /context in a fresh session and see how much is gone before you even type a word
your pocket will thank me later :<)
David Porkka retweeted
Meet Kimi K2.6: Advancing Open-Source Coding
🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)
What's new:
🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization).
🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D.
🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files.
🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops.
🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop.
-
K2.6 is now live on kimi.com in chat mode and agent mode.
For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code
-
🔗 API: platform.moonshot.ai
🔗 Tech blog: kimi.com/blog/kimi-k2-6
🔗 Weights & code: huggingface.co/moonshotai/Ki…
David Porkka retweeted
Introducing GLM-5.1: The Next Level of Open Source
- Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo.
- Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations.
Blog: z.ai/blog/glm-5.1
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.1
Coding Plan: z.ai/subscribe
Coming to chat.z.ai in the next few days.
David Porkka retweeted
this is so fucking wholesome
guy used AI to save his cancer-ridden dog by sequencing its DNA and creating a CUSTOM cure.
the tech behind this is fucking awesome (well done @demishassabis and the google team):
- used CHATGPT to sequence dogs DNA discovers mutations
- ran the mutations through Google’s Alphafold (AI protein sequencer) which CREATED A CUSTOM VACCINE TO TREAT THEM.
- treated dog and reduced tumour by 50% in WEEKS. dog is alive and well.
- this is the 1st time AI has been used to create a custom vaccine for a dog (and it worked)
- dude is now working on similar vaccines for humans using AI!
2026 is definitely the year we see AI change personalised medicine in a HUGE way
so sick
David Porkka retweeted
SOMEONE JUST OPEN-SOURCED A HEADLESS BROWSER BUILT FROM SCRATCH FOR AI AGENTS.
It's called Lightpanda. Written in Zig. Not a Chrome fork.
- 11x faster execution than Chrome
- 9x less memory
- Instant startup
- Drop-in replacement for Puppeteer and Playwright
Chrome was never built for agents running at scale.
If you're running 100s of AI sessions simultaneously, this is the difference between a $500/month infra bill and a $50 one
github link: github.com/lightpanda-io/bro…
David Porkka retweeted
What do they got?
A big team, lots of money, a strong brand, seemingly unlimited resources, panache, reputation, all that. They’re established.
They’re your competitors.
You want to look away, but you see them everywhere. Their ads on your social, their name in the media, your dream clients on their website.
But you know what else they got?
Bigger company bloat. Overflowing obligations. Narratives to uphold. Appearances to maintain. Entitlement. Too much overhead.
They’re slow. They’re conservative. They talk too much. They’ve stopped taking risks. They’re resting on their laurels, gliding on their reputation. They’re on defense.
What they’ve really got is a lot to lose.
What do you got?
Hunger. Drive. Grit. Scrappiness. Independence. You’re on offense.
You don’t have enough, which is why you’re dangerous. You have no choice but to be clever and creative. To make up for what you don’t have with something they can’t have: The underdog spirit.
You can move. You can adjust. You can adapt. You can get it done while they’re still stuck deciding what to do.
Small is not a stepping stone. Small is not less than. It’s greater than. It’s faster than. It’s better than.
Savor your position. You don’t get to be the underdog forever. The baton will be passed. But for now, it’s your magic wand. Use it.
We stand with the underdogs.
David Porkka retweeted
🚨 Someone just built a tool that turns any GitHub repo into an interactive knowledge graph and open sourced it for free.
It's called GitNexus. Think of it as a visual X-ray of your codebase but with an AI agent you can actually talk to.
Here's what it does inside your browser:
→ Parses your entire GitHub repo or ZIP file in seconds
→ Builds a live interactive knowledge graph with D3.js
→ Maps every function, class, import, and call relationship
→ Runs a 4-pass AST pipeline: structure → parsing → imports → call graph
→ Stores everything in an embedded KuzuDB graph database
→ Lets you query your codebase in plain English with an AI agent
Here's the wildest part:
It uses Web Workers to parallelize parsing across threads so a massive monorepo doesn't freeze your tab.
The Graph RAG agent traverses real graph relationships using Cypher queries not embeddings, not vector search. Actual graph logic.
Ask it things like "What functions call this module?" or "Find all classes that inherit from X" and it traces the answer through the graph.
This is the kind of code intelligence tool enterprise teams pay thousands per month for.
It runs entirely in your browser. Zero server. Zero cost.
Works with TypeScript, JavaScript, and Python.
100% Open Source. MIT License.
David Porkka retweeted
Pick any problem in your life. Now imagine you have an evil twin with a moustache. This evil twin is making it their sole focus to solve this problem before you do. What are they doing differently to you? Write this down. And then try to beat them. Hurry. They've already started.