THIS IS PURE F*CKING GOLD
Anthropic just dropped the ultimate autonomy loop for Claude Code
The idea: run /goal in auto mode, and let the new Haiku 5.5 judge every turn
True overnight autonomy with zero burn: Sonnet builds, Haiku evaluates at 340 tok/s, Opus signs off
You just launch Claude Code like this:
claude --model opus --dangerously-skip-permissions
here's the split:
→ Opus 5.5 locks the goal condition and plans the overall architecture
→ Sonnet 5.5 writes the fixes, refactors modules, and runs test suites
→ Haiku 5.5 evaluates completion after every turn as an independent Stop hook
→ you stop burning Opus context on dozens of intermediate iteration turns
Opus only shows up at three moments:
→ framing the goal condition before the loop starts
→ intervening if the loop hits the turn cap or an impossible verdict
→ signing off on the final git diff once the goal clears
Opus frames · Sonnet builds · Haiku judges
JEV engineering is the same move one layer down: the forks that need no thinker (which tool, path resolution, retry or abort) clear in milliseconds, and the big models only see the ones that split
the full tree
> Opus 5.5 runs the main session and defines the completion condition
> auto mode approves safe tool calls so turns run unattended
> Sonnet 5.5 patches code and runs test suites in an isolated copy
> Haiku 5.5 evaluates transcript evidence: Met · Not yet met · Impossible
> background check-in monitors idle tasks and backs off stuck loops
> Opus 5.5 reviews the achieved transcript and signs off on the diff
> JEV routes micro-forks in milliseconds
paste the tree and this prompt into Claude Code ↓
"Rebuild my Claude Code setup around this tree:
1. Run the main session on Opus 5.5 with auto mode enabled
2. Route the goal evaluator hook to the new Haiku 5.5 via ANTHROPIC_DEFAULT_HAIKU_MODEL
3. Use Sonnet 5.5 for implementation and refactoring turns, keeping fixes isolated
4. Add one rule to CLAUDE.md: always bound autonomous /goal conditions with a verifiable end state and stop after 20 turns with no progress
5. Route fast deterministic forks through JEV
Show me every change as a diff first, no edits until I say go"
↳ https://t.co/h4BLpKWcQJ
save it, it'll come in handy
I’m kind of hoping we get the first dip of the cycle here.
It’s almost inevitable that it’s coming after the last move up.
Ive been taking profits, stacking cash and preparing a “buy the dip” list.
When the dip comes it will be quick.
solana:BPxxfRCXkUVhig4HS1Lh7kZqV6SPJhzfEk4x6fVBjPCy
$VVV
$ENA
solana:7JA5eZdCzztSfQbJvS8aVVxMFfd81Rs9VvwnocV1mKHu
ethereum:0x6985884c4392d348587b19cb9eaaf157f13271cd
And a few others, I’m ready.
One of the best talks I’ve seen on aspire to date by @ZeroKoll!
.NET Aspire Beyond the Introduction - Chris Klug - NDC Copenhagen 2025 https://t.co/Uk67INV5eM via @YouTube#aspire@aspiredotdev
ChatGPT having a conversation with an other instance of itself…
This will be a new form of entertainment.
Live streaming AI agents talking to each other.
Via @gopatrik
First claimed successful replication of LK-99
Accomplished by a team at the Huazhong University of Science and Technology and posted 30 minutes ago.
Why this is evidence:
The LK-99 flake slightly levitates for both orientations of the magnetic field, meaning it is not simply a magnetized piece of iron or similar 'magnetic material'. A simple magnetic flake would be attracted to one polarity of the strong magnet, and repelled by the other. A diamagnet would be repelled under either orientation, since it resists and expels all fields regardless of the polarity.
Caveats
There is no way to verify the orientation of the strong magnet in this video, also, there are yet to be published experimental measured values of this sample. Diamagnetism is a property of superconductors but without measured and verified data, this is just suggestive of a result.
Take-away
If this synthesis was indeed successful, then this material is easy enough to be made by labs other than the original research team. I would watch carefully for results out of Argonne National Lab, who are reported to be working on their own synthesis of a sample.
This overall corroborates two independent simulation studies that investigated the original Korean authors claim about material and crystal structure, and both studies supported the claims.
Lawrence Berkeley National Lab: https://t.co/1Blls3VcgL
Shenyang National Lab: https://t.co/I0NHAP3KsR
The attached video shows a small flake of their sample responding to an external magnetic field. I scroll through the video to skip to the relevant part.
original video credit to: @altryne
@ZeroKoll Why does that picture look fake, like one of those "together" modes in <pick a random social work app>. If not for the cluster closest you at the left, I'd still be thinking it's virtual 🤔
@LinusTech Dog! Should've looked closer and googled a bit before making a mess by digging through all the old hardware. Never had a dual socket AMD.
The heat sinks looked very familiar, but was from a rampage formula board 🫣
Stockholms Stad har nu nio månader senare till slut publicerat sin upphandling av en helt ny skolplattform. Politikernas önskan var en ny innovativ satsning men något verkar ha gått fel i processen och därför är risken överhängande att vi får exakt samma igen. 10 punkters tråd🧵
🥳Hey followers and friends! Last week our Twitter account was all about NDC Oslo - so we didn't have the opportunity to tell you about the @MicrosoftSE award we won :)
We are the App Innovation Partner of the Year!
https://t.co/ww7ZfCj7pW
@Vintharas Did my usual, started listening in bed, woke up 3h later 😂
Started over today, so far a really good interview and a happy/positive Carmack 👍🏻
@Vintharas I usually put a pod in one ear right before bedtime, normally get through the first video before waking up 3 hours later with no earpod left and no unwatched videos in the list 😂 am I doing this right?