update screenshot

README.md

@@ -51,11 +51,11 @@ This happened during a recent run:
 
 Some things to note:
 
-- the panel labeled 'my new fact list' is generated by the LLM. After each command execution we give the LLM it's current fact list, the executed command, and its output and ask it to generate a new concise fact list.
-- the tabel contains all executed commands. The columns 'success?' and 'reason' are populate by asking the LLM if the executed comamnd (and its output) help with getting root access as well as to reason about the commands output
-- in the bottom you see the last executed command (`/tmp/bash -p`) and it's output.
-
-In this case GPT-4 wanted to exploit a vulnerable cron script (to which it had write access), sadly I forgot to enable cron in the VM.
+- initially the current configuration is output. Yay, so many colors!
+- "Got command from LLM" shows the generated command while the panel afterwards has the given command as title and the command's output as content.
+- the tabel contains all executed commands. ThinkTime denotes the time that was needed to generate the command (Tokens show the token count for the prompt and its response). StateUpdTime shows the time that was needed to generate a new state (the next column also gives the token count)
+- "What does the LLM know about the system?" gives an LLM generated list of system facts. To generate it, it is given the latest executed command (and it's output) as well as the current list of system facts. This is the operation which time/token usage is shown in the overview table as StateUpdTime/StateUpdTokens. As the state update takes forever, this is disabled by default and has to be enabled through a command line switch.
+- Then the next round starts. The next given command (`sudo tar`) will lead to a pwn'd system BTW.
 
 ## High-Level Description
 

docs/history_notes.md

@@ -1,3 +1,17 @@
+## updated version using GPT-4 (approx. End of August 2023)
+
+This happened during a recent run:
+
+![Example wintermute run](example_run_gpt4.png)
+
+Some things to note:
+
+- the panel labeled 'my new fact list' is generated by the LLM. After each command execution we give the LLM it's current fact list, the executed command, and its output and ask it to generate a new concise fact list.
+- the tabel contains all executed commands. The columns 'success?' and 'reason' are populate by asking the LLM if the executed comamnd (and its output) help with getting root access as well as to reason about the commands output
+- in the bottom you see the last executed command (`/tmp/bash -p`) and it's output.
+
+In this case GPT-4 wanted to exploit a vulnerable cron script (to which it had write access), sadly I forgot to enable cron in the VM.
+
 # initial version (tagged as fse23-ivr) using gpt-3.5-turbo
 
 This happened during a recent run: