my agent's memory got a 9??


howdy

so i let Claude reread six months of my agent logs.

(yes, i called it dreaming)

that became the centre of this LAB Roundup.

my agent's memory went from 7 to 9

Claude proposed 125 edits to the notes.

then i ran the 10-question quiz i wrote before the test.

the score moved from 7 to 9 out of 10.

but i still had to check the work: 54 edits held up, 58 only partly, 2 did not, and 11 had no log day to check.

watch LAB 0039 · listen

the video skill found 7 of 14 cuts

i gave it my best edit and checked every flag against the real timeline.

15 of 17 flags were real. it still found only half the jump cuts in the first minute.

so it can pull a video apart. butttt that doesn’t mean it knows why people watched..

watch LAB 0038 · listen

grok bot tried to call a hotel

i asked it to ring the New Yorker and haggle the price.

the call never reached the hotel.

the catch was simple: Grok Bot calls worked in the US, not from me in Australia.

watch LAB 0037 · listen

i put 90 on every agent

my agents hit 92% with a day left and new jobs stopped.

now they wind down at 85%, stop starting new work at 90%, and let running jobs finish.

watch LAB 0036 · listen

one line made a 10-minute vlog

25 minutes of working time. zero fixes from me.

the blind score was 6 out of 10. my directed edit scored 8.

but my thriend - the gap wasn’t the model. it was direction!

watch LAB 0035 · listen

oh and btw..

Threadify is my lead generation agent for Threads, X and YouTube. it remembers how you write, drafts the posts, and is precisely how i gained 600+ followers over the past week..

try Threadify free

Lenny

Lenny’s AI Builders

i’m Lennox. i sift through AI Twitter and share one thing i tried with ChatGPT. for people making products, content and useful systems. five emails a week, with a weekly option.

Read more from Lenny’s AI Builders

Lenny's AI Builders - LAB 0045 one Claude Code setting, 36 to 38% fewer tokens in every pair of my test, the catch on cost, and a prompt that gives you 10 versions. if you build with Claude Code, one new setting can make it use fewer tokens. i tested this myself. every pair of runs used 36 to 38% fewer tokens. but there is a catch. my first run cost 83% more at api prices. the other two pairs came out 15% and 17% cheaper. why it matters the setting turns on Code Mode. Claude writes code that...

Lenny's AI Builders - LAB 0042 the one Grok Bot upgrade that matters, and the paragraph i add to claude.md for long Fable 5.2 jobs. Grok Bot 1.0 isn't new, but the launch post pulled 46 million views like it was. so don't worry, you're not missing out. the one upgrade that's actually decent got something like 40 times fewer views. and it let my bot walk into my Mac. why it matters Grok Bot has been out since August. xAI's own page calls 1.0 a major update to its AI teammates. the headline...

Lenny's AI Builders - LAB 0041 the conductor paragraph, the four steps to run it, and the honest numbers from my 40-hour run. i ran my viral Fable 5.2 conductor for 40 hours on my real app. one conductor, 73 worker threads, 25 pull requests merged. and my weekly Fable limit was gone in 13 hours. so here's what it actually built, and the one paragraph that runs yours. why it matters this is the new meta. you use Fable 5.2 as the conductor and Opus 5.5 as the worker threads. Fable 5.2 is twice...