Med Machrouh 🇵🇸 @medmac01

In 2023, Prompt engineering taught us to talk to models. How to craft the right words to get better output. 2024 was all about Context engineering and thought us how to feed the model. What goes in the window? In what order? How much? Looks like 2026 is all about Harness engineering. The idea is pretty simple, yet very powerful: models are good enough nowadays (even local models) The constraint isn’t capability, it’s reliability. And reliability doesn’t come from a better prompt. It comes from designing an environment where failure is recoverable, mistakes don’t repeat, and the agent has enough structure to make consistent progress without us watching. Harness engineering is about building the environment the model operates inside.

🚨 صدمة أمنية لمعالجات آبل الجديدة! رغم استثمار آبل مليارات الدولارات وقضاء 5 سنوات في تطوير نظام MIE (Memory Integrity Enforcement) بمعالجات M5 و A19 للقضاء تماماً على ثغرات الذاكرة.. تمكن باحثون أمنيون باستخدام أداة "Mythos Preview" من اكتشاف أول ثغرة "Kernel" ناجحة وتطوير استغلال لها خلال 5 أيام فقط! 💻⚠️ أبرز ما جاء في التسريبات: ▪️ نظام MIE كان يهدف لتعطيل كافة سلاسل الاستغلال العامة، بما فيها أدوات (Coruna و Darksword) المسربة مؤخراً. ▪️ الباحثون قاموا بتسليم تقريرهم يدوياً في مقر "Apple Park" هذا الأسبوع. ▪️ سيتم نشر التقرير التقني الكامل (55 صفحة) فور إصدار آبل للتحديث الأمني المعالج للثغرة. ضربة تقنية قوية تثبت أنه لا يوجد نظام محصن بنسبة 100% مهما بلغت ميزانيات تطويره. 🛠️

Banger 😂

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.

Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask: "What do you think about xyz"? There is no "you". Next time try: "What would be a good group of people to explore xyz? What would they say?" The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".

Gemini 3.0 just refactored my entire codebase in one call. 25 tool invocations. 3,000+ new lines. 12 brand new files. It modularized everything. Broke up monoliths. Cleaned up spaghetti. None of it worked. But boy was it beautiful.

@aiwithjainam interested

I vibecoded this neural network visualization for my students and open sourced it. It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using @threejs and it comes with training code in @PyTorch . Link + repo 👇

OpenAI just killed 1,000,000,000,000,000 Startups 🤯

Bear witness, world. A mother being harassed in front of her kid by a POLICE officer in Morocco. This the country y’all intend to lodge in for the World Cup and the ACN #GENZ212 #GenZProtest #FREECHABAB #المغرب_اضحوكة_العالم

I'm noticing that due to (I think?) a lot of benchmarkmaxxing on long horizon tasks, LLMs are becoming a little too agentic by default, a little beyond my average use case. For example in coding, the models now tend to reason for a fairly long time, they have an inclination to start listing and grepping files all across the entire repo, they do repeated web searchers, they over-analyze and over-think little rare edge cases even in code that is knowingly incomplete and under active development, and often come back ~minutes later even for simple queries. This might make sense for long-running tasks but it's less of a good fit for more "in the loop" iterated development that I still do a lot of, or if I'm just looking for a quick spot check before running a script, just in case I got some indexing wrong or made some dumb error. So I find myself quite often stopping the LLMs with variations of "Stop, you're way overthinking this. Look at only this single file. Do not use any tools. Do not over-engineer", etc. Basically as the default starts to slowly creep into the "ultrathink" super agentic mode, I feel a need for the reverse, and more generally good ways to indicate or communicate intent / stakes, from "just have a quick look" all the way to "go off for 30 minutes, come back when absolutely certain".

In my opinion, it would be a HUGE MISTAKE for Iran to agree to this. Israel is just going to resupply. They have been running out of interceptors and IRAN maintains all the economic leverage to deter further US involvement. This just means Israel will come back stronger.

The UN estimates that 92% of *RESIDENTIAL* buildings in Gaza have been damaged or destroyed. That's beyond war, dude.

Jewish Tim Flack 𝕏 @tim_meh87

a year ago

@ZacksJerryRig People use the term genocide far too liberally these days. Going to war is not genocide, dude.

234 5 153 1.2M 7

Finally something not to be copied...

Tarun Vats @tarunvats33

a year ago

Samsung, please don't copy this; it looks bad 😫

496 276 7K 250K 181

Let’s stay focused on GAZA, where Israel continues to kill and inflict torment without respite. The images reaching those of us who choose to care are UNBEARABLE. "All children are our children,” Humanity said, seemingly in vain.

EU Parliament member Rima Hassan smiled throughout the entire “arrest,” looking the Israelis straight in the eyes. She posted previously: “When they come to arrest us, I will look at them the way Larbi Ben M'Hidi looked at the colonizers of his land: calm, confident in the liberation of Palestine. They are the occupiers of this land; we are its roots.”

keyboard_arrow_left Previous keyboard_arrow_right Next

عاجل| قوات الاحتلال تهاجم القارب #مادلين #لحظة_بلحظة #الجزيرة_مباشر x.com/i/broadcasts/1…

BREAKING: THE CREW OF THE MADLEEN FREEDOM FLOTILLA HAVE THEIR HANDS RAISED They are pointing guns at them #FreedomFlotilla

keyboard_arrow_left Previous keyboard_arrow_right Next

Filipe Neves ✍️🎶 @_FilipeNeves

a year ago

BREAKING: ISRAELI ARMY TOOK CONTROL OF THE MADLEEN FREEDOM FLOTILLA They made them put their hands up They have cut them off all communication. They have gone dark #FreedomFlotilla

0 1 1 2K 0