Mohammed Amer

Professional Account, passionate about using the latest technology available to digitally transform lives and businesses. No leisure/political talk.

[Mohammed Amer @MohammedAmerAI]

@OriSilver done

[Mohammed Amer @MohammedAmerAI]

I wired Codex into the Claude Code setup I already use. Official plugin, one ChatGPT login, /codex:review from the same session. Claude keeps building. GPT-6 does the second pass.Flow is simple. Freeze the tree, run codex exec --sandbox read-only against a prompt file (architecture, exclusions, P0/P1/P2 with file:line). Codex proposes. Claude checks each claim against the actual files, then patches and adds a regression. Tests still decide what ships.The point isn’t two models. It’s that the reviewer didn’t just write the change.Two things that bit me: exec can refuse and still exit 0, so I check the report file, not the status code. And I had to disable the plugin in cron or every scheduled job inherited it. --skip-git-repo-check only if you’re actually outside a repo.

[Mohammed Amer @MohammedAmerAI]

@OriSilver Done

[Gavin Baker @GavinSBaker]

Suspect we will start to hear about a “Pareto optimal” balance of computationally efficient humans, cheaper open-source tokens and frontier tokens.

Our internal AI spend @Atreidesmgmt will be roughly 100x higher in August 2026 vs. March 2026. Still roughly doubling every month. Note that is before Grok Bot moves to consumption pricing which will likely create a step function when it happens (at least for me).

AI means that scale has become more important to investing imo.

I think there will be a minimum token spend required to be competitive in most knowledge based industries.

The “compute inequality” referenced by Sholto in our discussion.

[Mohammed Amer @MohammedAmerAI]

@mikael_dereje Try the new concise options in settings

[Mohammed Amer @MohammedAmerAI]

@shirshakchavan I d work at anthropic even if it was less salary

[Mohammed Amer @MohammedAmerAI]

We code your app: $500
• We code your app while you watch: $800
• We fix the app you tried to "vibe code" with AI at 2 AM: $2,500
• You tell us "it's almost working, just one tiny prompt fix": $3,000
• You copy-pasted raw ChatGPT code without reading it and crashed production: $3,500
• You tried to let AI design your database schema on vibes alone: $4,000
• We build it from scratch using AI ourselves (the right way): $300

[Mohammed Amer @MohammedAmerAI]

Life with #AI Agents

[Mohammed Amer @MohammedAmerAI]

https://t.co/gF8qdD3eMf

2026 is definetly the maturity year where we start looking at the price tag and not just following the hype.

Great read

[Mohammed Amer @MohammedAmerAI]

Adulting in 2026:
Water
Heating
Electricity
Internet
Phone
AI tokens

The moment your AI bill starts rivaling your electric bill, you know the future arrived.

[Mohammed Amer @MohammedAmerAI]

Found my evening watch

[codila @0xCodila]

Google just released free 1-hour course on building agentic knowledge Graphs from 0% to 100%:

10% → 4:01 - how to build a GraphRAG agent
30% → 15:00 - Graph Engineering explanation
55% → 30:00 - Agentic search Engineering
80% → 35:48 - Graph Engineering practice
100% → 47:06 - self-improving agents in graphs

this free Google course mass replaces a $500 graph engineering bootcamp - learn it in 60 min to 100%

watch it today - then read the full graph playbook in the article below ↓

[Mohammed Amer @MohammedAmerAI]

This

[Andrew Ng @AndrewYNg]

Good move by @JensenHuang. The Nvidia letter is well written and worth reading. As we saw with the OpenAI-Hugging Face hack, we need open models and harnesses for defense.

Lets stop believing the PR that closed models are safer. - that's just regulatory capture.

[Mohammed Amer @MohammedAmerAI]

can't wait to try!

[Andrew Ng @AndrewYNg]

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry.

Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential.

OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose.

@rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think!

Try it out: https://t.co/P0mGnI1o31 (requires your own API key)
Source code: https://t.co/NYCiTD6hSq

[Mohammed Amer @MohammedAmerAI]

Most “vibe coders” are just mashing AI prompts like monkeys on ketamine.
The ones who actually cook? Seasoned developers and sharp, well-educated minds.
They understand what the hell they’re building, so their vibes turn into clean, scalable, non-hallucinated code. AI is a cheat code — but only if you’re not braindead. No knowledge = mid output.
Real expertise = That's where the multiplier is.

[Mohammed Amer @MohammedAmerAI]

🤣

[GitHub @github]

We heard you. And we agree.

In light of recent developments in physical media, GitHub is proud to announce that you can now obtain your public repo on CD-ROM.

Keep it. Lend it to friends. Pass it on to your children.

Your code is physically yours, forever. Until you lose it, let's be real.

Order yours today.
https://t.co/z041pdMH7h

[Anthropic @AnthropicAI]

We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5.

We'll begin restoring access tomorrow, and will share an update soon.

We’re grateful to our users for their patience, and to everyone who worked with us on redeploying the models.

[Femke Plantinga @femke_plantinga]

Skip transformer math to build AI agents in 2026.

You just need these 6 (+1) core architectural pillars.

𝟭. 𝗠𝗼𝗱𝗲𝗹 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗣𝗿𝗼𝘁𝗼𝗰𝗼𝗹 (𝗠𝗖𝗣)
Think "USB-C for AI." One universal standard that lets any agent plug into external tools and data — instead of hand-building an integration for every tool. Anthropic introduced it; the industry adopted it fast.

𝟮. 𝗔𝗴��𝗻𝘁 𝗟𝗼𝗼𝗽𝘀
The engine behind every agent. A cycle of: perceive → think → act → observe → repeat. The agent keeps looping until the task is done, or it decides it's stuck. No loop, no autonomy.

𝟯. 𝗦𝗸𝗶𝗹𝗹𝘀
The agent's job description. MCP handles the connection and tools expose the API, a Skill is the higher-level logic that orchestrates them into a finished outcome.

𝟰. 𝗦𝗶𝗻𝗴𝗹𝗲 𝘃𝘀 𝗠𝘂𝗹𝘁𝗶-𝗔𝗴𝗲𝗻𝘁 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲
Two ends of one spectrum. Single-agent: one LLM runs the whole pipeline. Multi-agent: specialized agents split the work, one retrieves, one validates, one writes, trading simplicity for scale.

𝟱. 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚
RAG with a brain. The agent can route queries to specialized knowledge sources, validate retrieved context, and make dynamic decisions about what information to use.

𝟲. 𝗔𝗴𝗲𝗻𝘁 𝗠𝗲𝗺𝗼𝗿𝘆
Short-term lives in the context window; long-term is pulled on demand from external stores (knowledge bases or vector databases). It's what keeps agents coherent across interactions, and lets them learn from past ones.

𝟳. 𝗛𝘂𝗺𝗮𝗻-𝗶𝗻-𝘁𝗵𝗲-𝗟𝗼𝗼𝗽 (𝗛𝗜𝗧𝗟)
The ultimate guardrail. Autonomous loops are powerful, but pure autonomy is dangerous for high-stakes tasks. HITL inserts human checkpoints for approval or correction before critical actions run.

Which term would you add? 🤔

[Mohammed Amer @MohammedAmerAI]

🚀 Testing what I believe is the ultimate hybrid AI rig on M4 Pro 48GB:• Local beasts: Qwen3-Coder 30B-A3B (primary agentic/coding), GLM-5.1 27B (long-horizon reasoning), Gemma4 26B (fast triage) — all via Ollama + MLX
• TrueFoundry AI Gateway + LiteLLM proxy for intelligent routing, virtual models, MCP tools & seamless fallbacks
• Local-first for 80%+ (RAG, high-volume ticket analysis, agents) → Claude/GPT-5/Gemini only on complex reasoningZero marginal cost. Full privacy. Frontier quality on demand. Local + Enterprise control plane = endgame setup

#LocalLLM #TrueFoundry #AIEngineering #M4Pro #AgenticAI

[Mohammed Amer @MohammedAmerAI]

Here are the direct GitHub links to the repositories for all the tools mentioned in the stack:

Caveman: https://t.co/4x60hPM6Gv

Ponytail: https://t.co/YADd9KoWpH

Token Optimizer: https://t.co/iffTwOV9sN

Claude Token Efficient: https://t.co/rcxDEBtLdE

[Mohammed Amer @MohammedAmerAI]

Bleeding API tokens in Claude Code? 💸

Drop these into your terminal for the ultimate cost-slashing stack:

🗣️ Caveman (kills all AI filler text)
🐴 Ponytail (writes the absolute minimum code needed)
🗜️ Token Optimizer (compresses context history)
📜 Token Efficient (stops over-engineering)

The best part? They don't conflict. They stack to create a ruthlessly efficient, money-saving AI dev. 🛠️🔥
#ClaudeAI #DevTools #Coding #SoftwareEngineering

Link in the 1st reply.