How do always-on, proactive agents like @Bot work? Watch my lecture at Stanford CS146S: 2:35 How we got here 6:13 What changed in the models 10:06 Inside an always-on agent 18:07 The harness 27:26 Context engineering 34:26 Where this is going

@bot huge

@bot Fire fit @leerob.

@bot Excellent talk.

@bot what changed in the models is mostly tool calling not breaking every third step

@bot DAMN! The goat has dropped.

@bot Stanford Lecturer!!! How cool

@bot Is it somewhere on YouTube?

@poteto @bot @bot requiero la transcripción de esta conferencia

@bot always-on is the easy part. knowing when not to ping you is the actual hard part

@bot let's go!!

@bot saving context engineering part for tonight

@bot Been following your content for a long time Watched the whole thing the always-on agent setup (server + VM, sub-agents, and keeping the main context sparse) is clear and practical The context engineering section at 27 min is the one I’ll rewatch

@bot I'm turning this lecture into a breakdown site: chapters, diagrams, the key ideas from the harness and context engineering parts. Will drop the link right here and post it once it's live. Also, hope we get to see you give this talk at Columbia someday 🙌

@bot @bot watch this for me and give me the summary

@bot proactive is the hard part. knowing when not to interrupt seems harder than doing the task itself

@bot 💡

@bot A lot to learn here. As mentioned, @bot harness returns errors like “the computer is asleep. wake it with the shell. then retry.” Our system returned a bare not_found, which is how it failed sometimes. Every tool should return a next step instead and not just fail.

@bot Yea, will definitely watch this later. x

@bot Thanks for the timestamps, convenient to pull out just the segments of the video that are interesting

@parkersmith @bot @bot save this

@bot always-on agents die on what they keep between wakes, not on the model call. the harness chapter is the one worth stealing.

@bot 🔥

@bot skipping straight to 18:07 lol

@bot 45 minutes on always-on agents and mine can't stay on through lunch

@poteto @bot @bot make a note to watch this

@bot Bookmarked for a quiet hour! Looking forward to learn a thing or two 🚀

@parkersmith @bot Bless us with a Cursor and Grok Bot reset pls sir.

@bot Looking forward to watching this over a coffee

@bot saving this one for later. the context engineering part at 27 minutes is what i'll watch first