pricing comparison between models its "agentic enginneering" not "vibe coding llm also generates the tests "I acknowledge the ethical issues BUT..." prompt injection deepseek is pretty good now json ralph loops "llms are just linear algebra" prompt injection "llms are just linear algebra" "check" output of LLM using another LLM adversarial process "check" output of LLM using another LLM markdown pricing comparison between models markdown 𝕏, the everything app "human in the loop" agent deletes the tests LLM generates docs for the LLM to consume llm also generates the tests its "agentic enginneering" not "vibe coding "let's ask Claude" "human in the loop" adversarial process agent deletes the tests pricing comparison between models its "agentic enginneering" not "vibe coding llm also generates the tests "I acknowledge the ethical issues BUT..." prompt injection deepseek is pretty good now json ralph loops "llms are just linear algebra" prompt injection "llms are just linear algebra" "check" output of LLM using another LLM adversarial process "check" output of LLM using another LLM markdown pricing comparison between models markdown 𝕏, the everything app "human in the loop" agent deletes the tests LLM generates docs for the LLM to consume llm also generates the tests its "agentic enginneering" not "vibe coding "let's ask Claude" "human in the loop" adversarial process agent deletes the tests
(Print)
pricing comparison between models
its "agentic enginneering" not "vibe coding
llm also generates the tests
"I acknowledge the ethical issues BUT..."
prompt injection
deepseek is pretty good now
json
ralph loops
"llms are just linear algebra"
prompt injection
"llms are just linear algebra"
"check" output of LLM using another LLM
adversarial process
"check" output of LLM using another LLM
markdown
pricing comparison between models
markdown
𝕏, the everything app
"human in the loop"
agent deletes the tests
LLM generates docs for the LLM to consume
llm also generates the tests
its "agentic enginneering" not "vibe coding
"let's ask Claude"
"human in the loop"
adversarial process
agent deletes the tests
