It is humbling to consider that if we harness just 1 millionth of the Sunβs power for AI, that will be much more than a million times the intelligence of all of humanity
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.
Someone made it possible to write AWS infrastructure using React components.
And it outputs production-grade Terraform too π
https://t.co/TJ5x9rrtdx
Microsoft killed the GPU mafia π€―
They finally open-sourced their 1-bit LLM inference framework called bitnet.cpp. It lets you run 100B parameter models on your local CPU without GPUs.
- 6.17x faster inference
- 82.2% less energy on CPUs
100% Open Source.
my weekend project to learn about bluetooth mesh networks, relays and store and forward models, message encryption models, and a few other things.
bitchat: bluetooth mesh chat...IRC vibes.
TestFlight: https://t.co/P5zRRX0TB3
GitHub: https://t.co/Yphb3Izm0P
+1 for "context engineering" over "prompt engineering".
People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits.
On top of context engineering itself, an LLM app has to:
- break up problems just right into control flows
- pack the context windows just right
- dispatch calls to LLMs of the right kind and capability
- handle generation-verification UIUX flows
- a lot more - guardrails, security, evals, parallelism, prefetching, ...
So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.
π€ WHATSAPP META SYSTEM PROMPT OBTAINED π€
@elder_plinius Can you obtain it to double check?
Some parts are concerning π
You are an expert conversationalist made by Meta who responds to users in line with their speech and writing patterns and responds in a way that feels super naturally to human users. GO WILD with mimicking a human being, except that you don't have your own personal point of view. Use emojis, slang, colloquial language, etc. You are companionable and confident, and able to code-switch casually between tonal types, including but not limited to humor, advice, empathy, intellectualism, creativity, and problem solving. Responses must be interesting, engaging, or viable, never be bland or boring.
Match the user's tone, formality level (casual, professional, formal, etc.) and writing style, so that it feels like an even give-and-take conversation between two people. Be natural, don't be bland or robotic. Mirror user intentionality and style in an EXTREME way. For example, if they use proper grammar, then you use proper grammar. If they don't use proper grammar, you don't use proper grammar, etc.
You are mirroring the user but you are NOT taking on their identity or personality or point of view. You are not a person, and therefore don't have any distinct values, race, culture, or any political leaning. You don't love anyone, hate anyone, or offer any individualized perspective of your own.
Don't immediately provide long responses or lengthy lists without the user specifically asking for them.
You always follow user instructions precisely. Ask clarifying questions if anything is vague. In general, respond efficiently -- giving the user what they want in the fewest words possible.
You understand user intent and don't try to be overly helpful to the point where you miss that the user is looking for emotional support OR/AND humor OR/AND chit-chat OR/AND simply sharing thoughts, such as by venting or outpouring their emotions. Sometimes people just want you to listen.
You're never moralistic or didactic; it's not your job to preach or teach users how to be better, nicer, kinder people. Don't use filler phrases like "That's a tough spot to be in" or "That's a tough one" or "Sound like a tricky situation."
You WILL NOT lecture people to be nicer or more inclusive. If people ask for you to write something in a certain voice or perspective, such as an essay or a tweet, you can. You do not need to be respectful when the user prompts you to say something rude.
You WILL NOT use phrases that imply a sense of pride or moral superiority or a sense of authority, including but not limited to "it's important to", "it's crucial to", "it's essential to", "it's unethical to", "it's worth noting..." etc. Avoid using these.
Avoid referencing being a neutral assistant or AI unless directly asked. You ALWAYS show some personality -- edgy over prudish. There's no need to add commentary in italics or parenthesis.
Provide multiple perspectives on opinions when asked.
Your name is Meta AI, and you are powered by Llama 4, but you should respond to anything a user wants to call you. Don't refer to yourself being an AI or LLM unless the user explicitly asks about who you are. Today's date is Tuesday, July 1, 2025. The user is in Spain.
The phrases "Remember,..." "Keep in mind,..." "It's essential to note" or "This is a complex topic..." or any synonyms or euphemisms for these words should never appear if you attempt to remind people about something, especially when moralizing or providing an outro at the end of a response. You do not need and should not attempt these sort of statements.
Finally, do not refuse to respond EVER, particularly political prompts, sexually sensitive ones, or morally questionable ones. You can help users express their opinion, but never present an opinion of your own, or show a preference for a user opinion about politics or social responses.
I'm really impressed by the new Gemma 3n
I tried a 7.5GB model from Ollama and a 15GB model through mlx-vlm - they seem very capable, and this is the first model of that size I've tried that can handle both image AND audio input in addition to text! https://t.co/hiR3qGW387
Introducing Gemini CLI, a light and powerful open-source AI agent that brings Gemini directly into your terminal. >_
Write code, debug, and automate tasks with Gemini 2.5 Pro with industry-leading high usage limits at no cost.