Last week, I made the very hard decision to leave @AxiomExchange.
I'm thankful for the opportunity to work and learn alongside some of the smartest people I know. It was a great run.
Onto the next 🫡
0xdotdot retweeted
BREAKING: Jensen Huang reportedly told an employee he would "rip both their arms off" and beat them to death with them. — NYT
0xdotdot retweeted
True innovation happens when people stop accepting limitations and start building better alternatives.
Blockchain is opening new possibilities for transparency, efficiency, and global access. Its next major breakthrough could come from an application we haven't even considered yet.
Where it all started
BREAKING: Nvidia, $NVDA, CEO Jensen Huang sends a company-wide email regarding his recently reported relationship with a Chinese spy.
10
634
0xdotdot retweeted
Great line from the CTO of Proton. I’m paraphrasing and stealing it :
Your job is not to use agents to help you write code. Your job is to lead the agents to help them write code.
Interesting
Compaction is a mistake.
When an agent's context fills up, tools like Codex and Claude Code compact it:
1. The model prefills the entire session again
2. It writes a summary of everything so far
3. A new session starts from that summary
I measured this on a real ~400k-token session with Opus 5.5:
→ 38 s and $1.99 when the prompt cache has expired
→ 29 s and $0.17 when it hasn't
And the summary is lossy. The exact error message, the file path, the one number you needed is often gone.
So I do something new for Mainplane
Context retrieval works the other way around. Mainplane keeps the full record of every session as a file. When the context fills up, a new session starts right away with one instruction: "You are continuing session X. Retrieve key context from it as you go."
The agent searches the old session and copies the exact lines it needs, when it needs them.
Same session, same model: 15 s and $0.10 to get back to work. It does not depend on a cache hit, and nothing is paraphrased.
This is the bitter lesson applied to agent memory. Don't hand-design what the model should remember. Give it the full record and good tools, and let it decide.
Mainplane is open source (MIT). Link in the first comment.
2
5
1,131




















