Seb Zuddas 🦄

@fatemallk Bullish

tinkering !! axiometa.io

I used to think prompt engineering was the unlock. I then trained an LLM from scratch, realising the real game is context engineering. The entire window shapes every output. Your clever prompt is just one small slice of it. Most people are still optimising the wrong variable. Here are some takeaways. First, start every chat with a clear why, and invoke the persona. One role. Keep the objective tight. If you don’t define it upfront, there is too much guessing. Those guesses compound across the context and pull the whole thing off track. And, when the model gets it wrong, don’t reply. Go back and rephrase your original prompt instead. Appending corrections pollutes the context window. Use forks or spin up a clean new chat. Second, every word is precious, each one shifts the output in embedding space. This is why ALL CAPS emphasis actually changes results. It’s not stylistic fluff. Precision compounds with every token you choose. Third, switch deliberately between expansive and contractive context. Expansive mode: explore every way this could go wrong, every option on the table. Contractive mode: pick one path and go deep.Most people drift in the blurry middle. The highest-leverage work happens when you choose the mode on purpose. Fourth, think in diamonds. Treat each stage of thinking as its own clean chat. Don’t drag exploration, decision-making, and execution into one messy thread. Give every phase its own focused context. Fifth, Memory hygiene matters. Delete chats that are wrong or stale. Memory-enabled models will happily drag old bad context into new conversations if you leave it lying around. The biggest unlock came from building the LLM myself. It made obvious why context is the primary performance lever. Everything else is secondary. These are the shifts that actually changed how I use models and agents every day. The full post is here: sebzuddas.substack.com/p/reflections-… →

@SystemsForScale More on the 'train an llm from scratch' - I really found it useful to understand the fundamentals and it changed how I interact with LLMs.

@SebZuddas 😊 Thanks for sharing your positive experience! What was it about TeleCommandCenter that made it so great?

10/10 would recommend

@disheartened_gy @EnemyCoastAhead Definitely contributed

@SebZuddas @EnemyCoastAhead That’s not what happened and that’s not ironic?

Hammersmith Bridge at sunset with no cars. Beautiful. Keep it that way.

Learn LaTeX

@lukas_m_ziegler @imperialcollege @ucl There’s more on this map ;)

Another week, another robotics map! 🇬🇧 This time, we will take a closer look at the busy streets of London and see what robotics companies are located there. London has excellent engineers and researchers, especially from universities like @imperialcollege and @ucl, which are well known for robotics, AI, and engineering. Many robotics founders and early employees come directly from these universities. London is home to @GoogleDeepMind, one of the world’s leading AI labs. Its work on robot learning, control, and general AI has helped push forward how robots learn and adapt in the real world. The city also has one of Europe’s strongest investor ecosystems. London is a major global finance hub, so it’s easier to find venture capital, corporate investors, and early customers, especially for robotics companies working in areas like logistics, healthcare, and automation. It is very international and business-friendly. It’s easy to hire talent from around the world, set up a company, and sell globally. → @TheHumanoidAI builds general-purpose AI-driven humanoid robots capable of physical tasks across domains. → @automata_tech develops easy-to-deploy robotic automation hardware and software for SMBs to reduce manual labor. → @shadowrobot creates advanced dexterous robotic hands and manipulation systems for research and industrial automation. → @PaddingtonR7 designs small autonomous robots for retail and service environments to assist staff. → @KAIKAKU_AI builds robotics and AI enterprise solutions to optimize warehouse and logistics processes. → Automated Architecture (AUAR) develops spatial computing and robotic systems that blend physical and digital environments for construction and design. → @recycleye creates AI-powered robotics that identify, sort, and automate recycling and waste processing, and has raised ~$20M+ in funding. → @Neuracore_AI builds AI-based perception and planning software for autonomous robots. → @apianhealth_ develops autonomous robotic systems for automated medication dispensing and hospital logistics. → @SlamcoreLtd offers high-performance SLAM navigation and vision software to help robots map and localize in complex environments, and has raised ~$6M+. → @MoleyRobotics builds fully automated robotic kitchen systems (“robotic chef”) and has raised tens of millions in funding (reports ~$30M+). → @dexoryHQ develops autonomous warehouse robots and AI software that continuously scan inventory and turn it into real-time operational insights, and has raised $80M Series B and a $165M Series C & growth round. → @extend_robotics builds tele-operation technology for robots, and helps with orchestrating the fleets of robots. → Cambrian Robotics develops AI-powered 3D vision software that gives industrial robots high-precision perception. → @engineered_arts builds highly expressive humanoid robots like Ameca for human–robot interaction, entertainment, research, and embodied AI applications. → All3 develops AI-powered robotic construction systems that automate building design and fabrication to reduce housing costs and construction time It seems that if you wanted to explore London from the perspective of robotic startups, it would take a few days! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news → ziegler.substack.com

@Yunsu_Tang Don’t understand either

the way i don’t understand football = the way they don’t understand taylor swift

@CharlieCheesma1 @oscarfalll It’s cause they’re working at light speed

real engineers wear sunglasses

@ogbuildsapps @ChihYang04 The world has changed 😂

@SebZuddas @ChihYang04 100% agree man, i once built an entire mobile ad serving platform + sdk for my employer in c# + swift, took me 3 months of solid solo work outside hours last night my friend showed me 6 mobile games he built with prompts over the weekend 🥲

solo founders/builders could you build your product by yourself without an llm?

Spec-driven development? You mean NASA's V-model. It's perfect for the agentic era - a clear, systems led approach. It starts by outlining how you'll address a need and validate that you've met the need. You then build comprehensive requirements, and implement. Now with AI.

@sashacayward Dream team

Hack commencing!!! The two non technical gals doing but things 🫡🫡

@MacdevM On it 😎

@SebZuddas Thanks! Yeah you should dive in🎉

Launched my third app StyleDeck and got the first paying user in just 1.5 days. Solid early validation. Grateful for the momentum. #StyleDeck #IndieDev #FirstSale #BuildInPublic

@MacdevM Success is a series of small wins that compounds

Closing today with $6.00🔥 still can’t express myself but even it is small win, it feels better than getting high salary, you can purely see that something you built helps to someone🚀

@georgecurtiss What gets you out of bed in the morning?

The wonderful thing about life is that it is truly and utterly meaningless. You can do whatever you want

“World models are a form of optimal control”

@lisa_aff I didn’t say it, it was the Greeks!

@SebZuddas Interesting what makes you say that

this may sound so peculiar but I have had this deep rooted fixation of studying mathematics out of the blue i finished my a levels a few years ago but I decided to study maths again randomly this year i have felt deeply emotional because mathematics, real mathematics, is not the dead thing they teach you in school it is alive, it is the structure of consciousness itself, the way the mind knows before it knows..it knows Mathematics has been pushed to be this complex puzzle of logic and numbers but in its simplest most beautiful form it is quite literally the explorations of relationships as you can imagine that is quite diverse therefore it literally is applicable to anyone whether you are a founder, a mechanic, a baker, a writer or an marketer that in itself sounds the least mathematical because it literally is mathematics was the exploration of all that we know from a single seed and there is something deeply non nerdy or non-complex about that