←
marwan239 posts
marwan avatar

marwan

@_marwanad

infra @cohere, prev @twitter, @azure (Azure Kubernetes Service)

◷ Joined October 2014▧ 7 Photos and videos
marwan avatar
marwan@_marwanad·Nov 10

the clowns have somehow managed to turn knowing how shit works into a productivity bottleneck

the clowns will never ever know the beauty and power of true knowledge and skill, which is still relevant in 2026, despite what the clowns want to make you think. don't be a clown. eat some humble pie while you're at it.

marwan avatar
marwan@_marwanad·Nov 9

you're really going to want your own semiconductor fab too

marwan avatar
marwan@_marwanad·Nov 8

any good cafes in tokyo where i can overhear people talking about agent swarms and harness engineering?

marwan avatar
marwan@_marwanad·Nov 7

pls for the love of god just build something people want before doing literally any of this

CANCEL your weekend plans. The 2027 meta just dropped. You NEED to: • Build a computer-use agent that parses the DOM, diffs screenshots and maps clicks to coordinates so it can drive legacy software with zero APIs • Ship generative UI where your LLM returns live React components instead of markdown blobs and watch your product feel 10 years newer • Wire a System-One router that resolves 95% of requests in milliseconds for fractions of a cent, escalating only the hard 5% to reasoning models • Kill your `while True` loop and rebuild it as a Temporal state machine that resumes from the exact node after a crash or a 3-day approval • Write a raw MCP server in pure JSON-RPC so any external agent can call your product with scoped credentials, no SDK required • Add grammar-constrained decoding so your agent emits 100% valid JSON on the first try, every try, forever • Build a trajectory grader in CI that blocks the merge the second a tool-call sequence deviates from the golden path • Ship an inter-agent sanitization proxy that executes prompt injections before they cross a single agent boundary • Wire a PII unmasking proxy that swaps sensitive data for UUIDs before inference and restores it after with full audit logs • Add a cost kill-switch that halts any loop projected to exceed $0.50 and degrades frontier → mid-tier → local → cache • Implement KV-cache prefix sharing at the gateway and cut Time-To-First-Token by 80% on repeated system prompts • Set up speculative decoding: local 3B drafts, frontier 70B verifies, acceptance rate logged on every single request • Shadow-route 5% of production traffic to your new model, diff trajectories and cost silently, auto-post the report to Slack • Automate the DPO flywheel: thumbs-down → preference pairs → nightly LoRA → eval-verified promotion, zero human touch • Build a voice loop with VAD and sub-1s interruption handling, streaming tokens and tool calls simultaneously • Ship an API-to-browser fallback that spawns a headless browser the moment a REST endpoint 404s, finishing the job anyway • Add a WebGPU shim so a 2B model runs in the browser when the cloud dies and your users never see a spinner • Fuzz your own agent swarm with malformed tool outputs and context overflow until it self-heals without a single pager alert • Publish one benchmark: your system vs the naive baseline, on cost, latency and task success, fully reproducible The wrapper era is over. The systems era pays. You have way too much to do. Bookmark & Repost.

marwan avatar
marwan@_marwanad·Nov 7

the future of agentic infrastructure is meat proxies at the edge, orchestrated from the meatpacking district

marwan avatar
marwan@_marwanad·Nov 7

strongest evidence of AGI i've seen

Thinking Machines' Inkling 2 Small has mastered a timeless debugging technique: saying "fuck" when nothing works. We analyzed 2,655 benchmark runs and found it swearing in 50 of them. Learn more in the blog linked in the thread.

Post attachment
marwan avatar
marwan@_marwanad·Nov 5

my ancestors worked the fields so i could sit around approving tool calls

marwan avatar
marwan@_marwanad·Nov 2

finally my agent can doomscroll on my behalf

Introducing: Phone Harness MCP 🔌 Any agent that supports MCP can now control a real iPhone or Android in the cloud: > works in Claude, ChatGPT, Cursor, Codex, and more as a custom connector > nothing to install, just paste a URL and sign in > sees the screen, taps, types, and swipes like you do Available in phone-harness 0.3.3. github.com/phone-harness/mcp

0:20
marwan avatar
marwan@_marwanad·Nov 2

reading code was always the job. writing it was the fun part we got to keep for a while.

Reading code is what makes you a good programmer. I've read, so so much code. Bad and good.

marwan avatar
marwan@_marwanad·Nov 2

finally someone solved the cold start problem

‼️ Hackers Hijack Swedish Supermarket Fridges and Raise Freezer Temperatures to 55°C Details: cybersecuritynews.com/superm… Hackers have reportedly targeted refrigeration systems at Swedish supermarkets, leaving stores with spoiled food after freezers reached temperatures as high as 55°C. Several ICA locations and six Coop stores were affected overnight into November 2, forcing staff to clear damaged stock and restore cooling systems. The incidents follow similar attacks against French supermarkets in October, although no connection has been confirmed. The ICA store in Sjöbo temporarily closed after reporting temperatures around 50°C. #CybersecurityNews

Post attachment
marwan avatar
marwan@_marwanad·Oct 30

coding agents are just slot machines that occasionally produce working software

Thariq@trq212Oct 29

There’s 100% a kind of mania you can get into with coding agents, where it feels like you’re getting a lot done and working all the time but nothing is really happening. I think it's often a form of avoidance of something else in life.

marwan avatar
marwan@_marwanad·Oct 29

can't wait for LGTM.md to drop

Are there any emerging/de facto standards for customizing AI code reviews (à la AGENTS.md, but for code review specifically, not general development)?

marwan avatar
marwan@_marwanad·Oct 28

we no longer do coding interviews, we just ask how many agents you have running in parallel