It is becoming f*cking dangerous: Microsoft Research made Claude Code 23.6% cheaper by letting it…
13K followers
28,557 views
10 Comments
Comments from the original post on X (Twitter)

@MerrCat001
Well the hard part is keeping it lean, im feel like im forever chasing this.

@KirSolo193083
the repo list is useful

@TolikWeb3ep
turning session history into hard rules and running lightweight subagents without context bloat turns development into ultra cheap and fast pipeline

@Kturt1
Fresh memory and context pruning tools turn AI agents from forgetful rookies into cost efficient pros

@thesimaximalist
Repo memory needs a way to retire stale facts. After a refactor, yesterday’s helpful note can become tomorrow’s repeated mistake. Linking notes to the code they describe gives you something concrete to check when it changes

@Kaggii_
all 7 repos being under 6 weeks old is worth a read before installing. several of them write into CLAUDE.md, so check what they change first

@Novlyx
Learning from past sessions only pays off if the bad lessons get cut too. Otherwise it just gets cheaper at repeating the wrong thing

@luxurycachecom
Caching?

@CODE_AIfa
Learning from past sessions is great until one session was poisoned — then the agent keeps "remembering" the attacker. Worth pairing with a guard at write time: PADAM NOCTURNE holds planted instructions for review, masks keys before storage, and lets you forget a single record provably.

@frankiewuxyz
the cli is quietly becoming the agent's memory. CLAUDE.md, session logs, skill files. i run most of my week through it. the biggest gain wasn't any single tool, it was the agent remembering what i corrected last time.
