Flak πŸš€ @construct-spaces (@flakerimi) header
Flak πŸš€ @construct-spaces (@flakerimi) profile picture

Storyteller, creator of https://xitter.gq/t.co/l72XxC9hcp

Ferizaj, Kosova
Joined October 2008
Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)Photo by Flak πŸš€ @construct-spaces (@flakerimi)
I think the evolution of LLMs is more interesting when you look at what everyone contributed along the way. OpenAI released ChatGPT and suddenly LLMs had an interface everyone could understand. Then RAG took off. Instead of relying only on what was inside the model, we started giving it external knowledge at runtime. Then function calling turned LLMs from something that could only answer into something that could actually call software. ReAct gave us the reason β†’ act β†’ observe loop. Reasoning models pushed inference-time compute. The model could spend more compute on the problem instead of immediately answering. Then Anthropic introduced MCP, which gave models a common protocol to discover and interact with tools and external context. Instead of every AI app building every integration again: LLM ↔ MCP ↔ world Then coding agents showed what happens when you put all of this together. Give the model a terminal, filesystem, tools, enough context and a loop and it stops looking like a chatbot. Then came skills. And I think skills are bigger than they look. Tools tell the model what it can do. MCP tells it how to connect to things. Skills tell it how to do the job. Add memory, subagents, computer use, verification and persistent environments and the architecture starts looking very different: LLM context reasoning MCP tools skills memory agents environment verification The LLM is becoming just one part of the system. We started with: prompt β†’ LLM β†’ text Now we’re getting closer to: goal β†’ understand β†’ plan β†’ act β†’ verify β†’ result And I think the next step is the environment itself becoming AI-native. Not an AI app running on top of your OS. An OS where models, agents, skills, tools, memory and your applications are all part of the same environment. That’s what LisaOS is all about.
1
1
2
180
Flak πŸš€ @construct-spaces retweeted
207
3,351
206
42,638
1,213,980
I laughed so hard I cried. God damn this was well done.
311
2,418
379
14,587
1,937,432
I’ve become scary in ai world, I understand more than I should
36
Flak πŸš€ @construct-spaces retweeted
Applications are now open for the Anthropic Residency, a paid, fixed-term research program for academics, technical founders, and staff-level engineers who want to make AI safe and beneficial for everyone. No ML background is required. Apply by November 22: alignment.anthropic.com/2026…
1,232
3,214
936
40,527
14,960,399
Your 5-hour limit has beenΒ removed
36
George Orwell warned us about 'Big Brother' watching us. We just didn't realize he meant it literallyβ€”Silicon is Carbon's bigger brother on the periodic table, and he's running the algorithm. Hit me while listening to @StarTalkRadio periodic table
25
I made a serious mistake: the cd failed, so the find … rm -rf executed in the root instead, wiping out repositories -Fable it’s been a while since this but fable has gone crazy
42
Just finished Diplomat S4, does it mean that US is not ready for Female President
1
46
No php code found, go go go!
2
85
From:”we are not going to deploy agents code in production without human review” To: β€œ We are not going to deploy human code in production without agent review β€œ
2
78
This is no different than Adobe. Lame.
1
1
89
Model Reads a lot, writes a little. We need to fix that.
52
Argon is good, but medium effort feels like max effort in Fable, so it just thinks more, and eats tokens like crazy, meanwhile Wonder is almost good but less tokens, worth keeping around.
33
Tell your AI to make a new material lighter and stronger than what we have already
1
38
Number of people building software compared with number of people using it is damn high, most of people are still: β€œI asked chat”
Software is dead It's now the era of personal software and everyone just builds what they need whenever they need it I think
41
Its not about Capitalism or Socialism, I know both, it’s about GREED
It's very important that we don't concede open source to socialists and communists. Capitalism is the greatest engine of growth and prosperity the world has ever seen. Open source is a great technique for aiding and accelerating it.
1
1
68