will to code

Evolution is nature's way of finding product market fit

- Charles Darwin

Anthropic's research Post on X

I strongly believe smart context management would positively impact our AI workflows > You tell AI write some code > It writes code > Code has error > You tell it to fix the error > It fixes it But now that "fixing" is in the context and sitting there not contributing to anything. What we need is this: > It goes back to the earlier code it sent > Adds the fix there > Deletes the messages of you telling it to fix the code We don't know anything at this point. What if it just follows the pattern of making a mistake and you telling it to fix it. Or like Antrhopics recent research what if it just takes on the personality of a sloppy dev... What if there was an agent which goes through the context and makes sure that the LLM's 'personality' is competent. The context manager decides what the long and short term memory needs to be. Dynamic context. Kinda like us.

The hardest thing in the world is simple

We need to bring back blimps Its one of the most exciting modes of transport to come out of a dynamic era Think about all the advancements in AI and nano tech... Autonomy, Efficiency and very hard to crash... Its better than telling people to go on autonomous planes which are practically cruise missiles.

Karpathy is soooo right > How good is your planning? > How good is your short/long term memory? > How much do you care? Imagine creating a detailed memory palace on what you want to get done and constantly updating it... Literally GOD MODE (...also being able to recall past sessions 🫠) The landscape has completely changed Those niche skills matter more than anything now

If I was an investor and had the opportunity I would happily invest 100% of my portfolio into major ai companies (open ai, anthropic, groq, moonshot...) even at this stage The sentiment right now is that they are bubbles about to implode My gut tells me otherwise

Neurons that fire together wire together

irl prompt injection 😆

I don't know how I missed this gpt 5-4 mini beats claude in coding and the open source labs are just around the corner

You now have the computational power in your laptop of which a few decades back was the pinnacle of what scientists could run their experiments on This is not an ad for Morse Law What I want to emphasize is that now you have, not only more compute than those scientists but also more intelligence in your hands I never cared about CPU before I only looked at the GPUs (for gaming) But now i am so grateful for my beloved cores Thank you intelligence in the sky Thank you Morse law 🙇

Before you strike your enemy Ask Claude where to strike - Sun Tzu

It's as if the scientific method was created for agentic systems!!! They could utilize it better than US!!! Do you realize how insane that is

The implications were always insane we just always ignored them human ignorance remains undefeated

Do not be distracted by the current thing Do things Nothing every happens

Problem solver or Solution user What will it be anon?

Deepseek used to be my philosophy model Now its my go to model for solving complex problems that other models struggle with

Minimax 2.7 best price/performance model > Swarms are becoming cheaper and more intelligent We need a Morse law for the Green Quadrant lol There will soon come a time when the swarm gets so cheap and intelligent that we make scientific discoveries through sheer brute force... like major ones. In a closer timeline than you think. And will also probably be done with an open weight model. Context window and response times also need to improve. Imagine the agents writing and peer reviewing each other's paper I bet you it would be higher quality than most papers that get published... so how could they not make major scientific discoveries Most people are lazy and are already using AI to write papers

The Golden age keeps on giving > Xiaomi? cooked > Minimax 3 will prob be crazy good Be Xiaomi > Copy Apple > Then do more shit