Ramya Chinnadurai 🚀

8.2K posts

Ramya Chinnadurai 🚀 banner
Ramya Chinnadurai 🚀

Ramya Chinnadurai 🚀

@code_rams

Building with AI agents in public. Cofounder @TweetsMashApp + LinkedMash(https://t.co/pbOsWhbhaB). Sharing what actually works.

Planet Earth انضم Haziran 2020
504 يتبع13.6K المتابعون
تغريدة مثبتة
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Turning 29 today 🥳 - Built two SaaS products. - Became a first-time mom. - Bootstrapped every line of code. - Balanced baby milestones with user feedback. My biggest lesson? You can build slow, messy, beautiful things and still be on the right path. Here’s to a year of softness, strength, and showing up, as me. What’s one life lesson you learned this year?
Ramya Chinnadurai 🚀 tweet media
English
215
191
4.1K
163.1K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
The US just suspended Fable 5 and Mythos 5 for every foreign national worldwide. My access went dark overnight. The catch nobody talks about: building on US AI infrastructure means a government directive can change your stack by morning. The 'build sovereign' crowd just got louder.
Anthropic@AnthropicAI

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

English
0
0
1
539
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Most people run AI agents one task at a time and babysit every run. The leverage is in the loop, not the model. A maintenance loop that actually scales: 1. Run an orchestrator on a timer instead of hand-prompting one job at a time. 2. Split work across threads so several tasks run in parallel and you steer instead of execute. 3. Add a triage skill so it decides what to work on next, not just what you typed. 4. Wire in autoreview so output gets checked before it lands, not after it breaks. 5. Let safe, reversible changes land on their own and gate the risky ones behind you. The win for a solo founder is a system that moves while you sleep, not a smarter model.
Peter Steinberger 🦞@steipete

Here's a simple loop: Tell codex to maintain your repos, wake up every 5 minutes and direct work to threads. That makes it easy to parallelize+steer work as needed. I use a orchestrator skill combined with my triage+autoreview+computer use skills, so some work can land autonomously. github.com/steipete/agent… github.com/steipete/agent…

English
0
0
1
371
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
@DeRonin_ Looks cool, so what does the agents actually do? How do they communicate with each other or how you orchestrates the tasks?
English
0
0
0
389
Ronin
Ronin@DeRonin_·
Claude Fable 5 (MAX) created a city where I'm a mayor who orchestrates 1,000 civilian agents spent 75 minutes, 324k tokens and now i manage everything from one common chat with my agentic residents: - getting reports in 3D papers what's hyping now in tech sector - every real task from my todo list becomes a construction site, a crew of agents builds it in 3D while i do the actual work - the tower only tops out when i mark the task done IRL, so my skyline is literally my productivity history - clicking any citizen in the world to give them direct orders ("go to site 2", "follow", "report") - typing "status" in the morning and the whole city reports back: deadlines, stalled sites, idle workers - "everyone build site 1", mass rerouting the swarm to my most urgent deadline - procrastinated tasks stay as empty dirt lots in the middle of downtown. visible shame works lol - closed a deal yesterday and ordered all 1,000 of them to dance no game engine, no API costs for the agents, pure simulation + chat parser
Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.

English
37
5
118
16.6K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
AI has written like a typewriter since day one: one key at a time, no backspace. Google's new DiffusionGemma writes like a draft instead. It dumps a rough block of text, then edits it into shape: 1. Whole paragraphs at once, not word by word. Up to 4x faster. 2. It fixes its own mistakes while writing, instead of being stuck with the first guess. 3. It runs on a single consumer graphics card, not a data center. 4. Free and open under Apache 2.0, so anyone can run it themselves. Why it matters even if you never touch the code: fast, local, and free together means smaller builders can run real AI without an API bill they do not control. The catch: it is experimental. Speed is easy to show off. Whether the writing quality holds up is the part still unproven.
Google@Google

Meet DiffusionGemma ⚡ Our latest experimental open model (Apache 2.0) that generates text up to 4x faster. Instead of predicting and typing just one word at a time like most language models, it drafts and refines entire blocks of text simultaneously. Here’s how it works 🧵 ↓

English
0
0
2
435
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Anthropic just shipped the most capable model they have ever released to the public. The clever part is not the raw power, it is how they handled the risk. What Claude Fable 5 actually changes: 1. It is "Mythos-class", a tier that until today only ran inside Anthropic. First time this level is open to everyone. 2. Built to run for days, not minutes. It plans across stages, hands work to sub-agents, and checks its own output. 3. Stripe tested it on a 50 million line codebase and ran a migration in one day that would have taken a team two months by hand. 4. Costs $10 per million input tokens and $50 per million output. Worth it for heavy long projects, overkill for small daily tasks. 5. The safety move: dangerous queries like cybersecurity or biology do not get refused. They quietly get answered by a weaker model, Opus 4.8, instead. Refusing every risky question looks safe but punishes real users. Downgrading only the dangerous edge while keeping full power everywhere else is the smarter call.
Claude@claudeai

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.

English
1
0
3
419
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Putting Claude on autopilot is the easy half. The half nobody sells you is the brake. Wrote the honest version: a 7-step stack for running Claude while you sleep without waking up to a mess. The engine, runs it: → /loop, find it in a throwaway session first → promote, session then desktop then cloud, earn each tier → budget, cap tokens and match the model on every fire → /goal, give the loop a real stop condition The brake, keeps it safe: → red-team the plan before the loop runs it → ship-check the output against what you promised → scope permissions by cost to undo 4 steps are the engine. 3 are the brake. You need both. Full breakdown in the article.👇
GIF
Ramya Chinnadurai 🚀@code_rams

x.com/i/article/2063…

English
3
0
16
1K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
@degensing For reads - 1 auto retry, then log and alert. For writes - no auto retry. Manual review before rerun. The failure I want to avoid isn't the task not running. It's the task running twice and doing something twice.
English
0
0
0
13
Degen Sing
Degen Sing@degensing·
@code_rams This is wild. Curious how you’re handling latency and retries?
English
1
0
1
60
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Most second brains are write-only. You save notes for years, then never find them again. An agent that can actually work inside your vault changes that: 1. Skills over plugins: Claude learns Obsidian syntax natively, wikilinks, embeds, callouts, properties. 2. It writes .base files for you, real database views across your notes with zero manual setup. 3. The agent can read, write, and reason inside the vault, not just answer questions about it. 4. Files stay plain markdown on your disk, so there is no lock-in and nothing to migrate. 5. 27,000 GitHub stars in days, the demand was already there. A vault you can search is a library. A vault an agent can edit is a teammate.
CyrilXBT@cyrilXBT

THE CREATOR OF OBSIDIAN JUST TURNED YOUR NOTE VAULT INTO AN AI AGENT. Not a plugin. Not an integration. A full agent skills system that teaches Claude Code, Codex, and OpenCode to READ, WRITE, and REASON inside your Obsidian vault like a power user. 27,000 GitHub stars in days. Here is what shipped at launch: obsidian-markdown — wikilinks, embeds, callouts, properties, the full Obsidian flavor Claude now understands natively. obsidian-bases — Claude can create .base files with views, filters, formulas, and summaries. json-canvas — Claude builds .canvas files with nodes, edges, groups, and connections. obsidian-cli — Claude controls your vault, develops plugins and themes directly from the terminal. defuddle — strips web pages into clean Markdown so you stop burning tokens on clutter. Install the whole thing in one line: npx skills add github.com/kepano/obsidia… Then connect it to Claude Code, Codex, or OpenCode. That is it. Your second brain now has an agent inside it that understands how Obsidian actually works. Not a generic AI that pastes text into files. An agent that knows what a wikilink is. What a callout is. What a canvas is. Built on the open Agent Skills spec. MIT license. Free forever. The gap between people using Obsidian as a note app and people using it as an AI operating system just got wider. Bookmark this before you open your vault today. Follow @cyrilXBT for every build that changes how Obsidian and Claude work together.

English
0
0
8
1.3K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
This is exactly why I built @TweetsMashApp Bookmarking is easy. Going back is the hard part. Tweetsmash turns your dusty bookmarks into: → AI digests & summaries → Auto-categorized insights → Agent-ready (Claude / OpenClaw / Gemini direct search) with MCP and API support → Export to Notion / Google sheets / notes No more “long bookmark” guilt 🚀 Try it: tweetsmash.app
English
0
0
1
87
GREG ISENBERG
GREG ISENBERG@gregisenberg·
Bookmarking tweets and not going back to them has become an epidemic
English
695
170
2.9K
435.1K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
A single agent running 50 tasks is one person who quits at task 20 and reports it done. A dynamic workflow is a team. One writes the plan. A fleet runs it, one job each. A separate agent tries to break the result. No agent audits its own work. The goal never drifts. Turned a 45-minute job into 8 minutes for me this week. Full breakdown in the post.
GIF
Ramya Chinnadurai 🚀@code_rams

x.com/i/article/2062…

English
4
5
50
11.4K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Problem Claude Code solves with Dynamic Workflows: Default harness = plan + execute in same context window. Works for coding but breaks for long, complex, parallel tasks. 3 specific failure modes it fixes: 1. Agentic laziness - Claude stops at 20/50 items and calls it done 2. Self-preferential bias - Claude prefers its own output when asked to verify itself 3. Goal drift - Long sessions + compaction = original constraints get lost How workflows fix it: - Claude writes a custom JS harness on the fly for the specific task - Spawns separate agents, each with their own context window + focused goal - Can choose which model each sub-agent uses - Can run agents in isolated worktrees - If interrupted → resumes from where it left off Examples from the article: - Mine flaky test root causes (run 50 times, form + test theories) - Extract CLAUDE.md rules from 50 past sessions - Find recurring Slack bugs with no tickets filed - Tear apart business plan from investor/customer/competitor POV - Rank 80 resumes + interview you for a rubric - Rename a model across entire codebase Key line: "Dynamic workflows often use more tokens - think carefully about when and how to use them."
Ramya Chinnadurai 🚀 tweet media
Thariq@trq212

Workflows are the biggest upgrade to Claude Code’s capabilities since skills and subagents. I dove deep into it with @sidbid to figure out best practices, examples and more.  I’m particularly excited about the non-technical tasks it enables for Claude Code.

English
1
0
12
1.1K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Pain Point I feel daily is, 1. Switching between browser tabs when running agents across multiple machines wastes time 2. The web version lacks native speed and feel 3. Setting up remote environments (Mac Mini, VPS) makes config syncing difficult 4. Daily Hermes users lose productivity without a polished desktop experience This release directly addresses these pain points. Hermes Desktop benefits: 1. Full native desktop app - chats, skills, and configs come along automatically 2. Remote Gateway mode is fully supported - point it at a backend running on Mac Mini or any server 3. Available on all platforms (macOS, Windows, Linux) 4. Zero migration for existing users - just download and log in This desktop version will be especially useful for client work involving multiple agent setups. The remote gateway mode is particularly valuable since heavy agents run on a Mac Mini in my current workflow. Looking forward to a more stable version soon. Already testing the public preview.
Nous Research@NousResearch

The next evolution of Hermes Agent is here! Introducing Hermes Desktop: everything you love about Hermes, now native on your machine. First demoed in Jensen's GTC keynote, it's now in public preview.

English
1
0
9
1.1K
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Chasing a new agent framework every month instead of shipping is the most expensive mistake builders make right now. Karpathy's dead list - what's already fading: 1. AutoGen, CrewAI, general agent frameworks.. demos break on real data 2. Agent marketplaces.. too abstract, no specific buyer 3. Benchmark leaderboards.. optimized for evals, not production 4. Horizontal "build any agent" platforms.. add abstraction, remove nothing 5. Per-seat pricing for agents.. wrong unit entirely The tools that survive: narrow scope, real workflow, one measurable outcome.
0xMorty@0xMortyx

Andrej Karpathy: "90% of what AI twitter tells you to learn will be dead in 6 months" 90% of what ai twitter tells you to learn dies in 6 months senior engineers already stopped chasing it the dead list: autogen, crewai, autonomous agent pitches, agent marketplaces, benchmark leaderboards, semantic kernel, dspy as a general framework, horizontal "build any agent" platforms, per-seat pricing for agents the pattern is obvious. demos that break in production. hype that never ships. frameworks that go viral on monday and vanish by spring what actually compounds: context engineering tool design orchestrator-subagent pattern eval discipline the harness mindset. harness > model, always mcp as the protocol layer the edge isn't the newest framework. it's staying a few steps ahead until your signal becomes everyone's mass-opinion book and study this

English
0
0
4
689
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
Garry built 540,000 lines of Rails to babysit an LLM. That's the Foxconn factory he's describing. Every retry loop, every validator, every guardrail, a bet that the model will fail. Here's what most builders miss: The old economics: model calls were expensive, code was cheap. So you wrote code to ration the model. That equation flipped. Models are cheap. Models write usable code. The architecture should flip too. The new artifact: 1. A markdown file with the intent and the skill 2. Minimal code for the parts that must not hallucinate 3. A test That's it.
Garry Tan@garrytan

x.com/i/article/2061…

English
1
0
2
501
Ramya Chinnadurai 🚀
Ramya Chinnadurai 🚀@code_rams·
This week I hit rate limits faster than expected. Turns out it was a bug, not my usage. Anthropic just reset limits for all Pro and Max users. Good reminder: when something feels off with your tools, check if it's actually your fault. Sometimes it isn't. Its time to burn more token! 🚀
Ramya Chinnadurai 🚀 tweet media
ClaudeDevs@ClaudeDevs

We've reset 5-hour and weekly rate limits for all users on Pro and Max plans. We fixed an issue that caused some Claude Code sessions to spawn excessive parallel subagents, burning through usage faster than expected.

English
0
0
7
860

اكتشف

@DeRonin_ @embw_l0x @pramodk73 @degensing @TweetsMashApp @elonmusk @BarackObama @taylorswift13