Andrej Karpathy:
"Prompting is going away.
Delete everything, keep Graph."
In 1 hour he explains how to build Graphs, and why it's the only thing that will be left standing at the end
LLMs → Prompts → Agents → Graphs
a prompt gets you one answer and forgets the job
an agent finishes the job and forgets what it learned
a graph saves every finished job and turns it into the starting point for the next one
watch it today
then save the full guide on Graphs below before everyone catches up ↓
THIS IS A PURE F*CKING GOLDMINE
Anthropic just shared one of the best tricks for Claude Code.
The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it.
Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer.
You just launch Claude Code like this:
claude --model opus --effort ultracode
here's the split:
→ Opus 5.5 turns your task into a workflow script
→ Haiku 5.5 agents scan every file in parallel
→ Sonnet 5.5 agents patch each fix in its own isolated copy
→ you stop burning Opus context on a hundred agent transcripts
Opus only shows up at three moments:
→ writing the workflow before the run
→ reading the verified results after it
→ signing off before anything ships
Opus plans. Haiku scans. Sonnet ships.
JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split
the full tree
> Opus 5.5 runs the main session and writes the workflow
> scan audits every file on Haiku 5.5
> edit patches each fix on Sonnet 5.5 in an isolated copy
> verify cross-checks every finding on Sonnet 5.5
> Opus 5.5 reads only what survived verification
> 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 ultracode on.
2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy.
3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress.
4. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. No edits until I say go."
↳ https://t.co/1MiKDqGANA
save it, it'll come in handy.
A drone captured the incredible moment a whale pushed a paddleboard with its fin.
Maximiliano Jonas filmed the amazing footage off the coast of Puerto Madryn, Argentina
[📹 maxijonas]
If you work with .mkv files on macOS, Quick Look is annoyingly limited. This should help a bit:
https://t.co/NMqQazO6Y5
A QuickLook extension vibe-coded with Claude + Codex. Supports mkv, webm, ogg, opus, VP9. And sometimes even avi.
#macOS#QuickLook#mkv#IndieDev
I’ve always missed a simple “New Text File” option in the macOS right-click menu. So I vibe-coded it with Claude + OpenAI. Here it is, in case you missed it, too:
https://t.co/NEzGJOz57B
Works on macOS 14, 15, and 26.
#macOS#OpenSource#Productivity#rightclick#newtextfile
@AnthropicAI deleted ALL of my billings and along with i my pro account for 200USD three days ago. Even though I contacted them saying it is URGENT, there is no still no answer! Typically a FAST MONEY MAKER company! SHAME ON ANTHROPIC!