Sabitlenmiş Tweet
I just open sourced some software that levels up claude code github.com/Spacehunterz/E…
English
JLad
287 posts
JLad
@josh_ladner
Love is to peace, as hate is to war. We need more love in the world. -If you are reading this you are a cyborg like me-
Katılım Temmuz 2014
489 Takip Edilen132 Takipçiler
English
Turns out with claude code, my decades long strategy of NOT deeply learning:
- regexs
- sql
- nginx confs
- elaborate shell commands
- advanced shell scripting
- any javascript framework
- perf optimization
- webpack, cdns, bundlers
- 1000 other things
...was entirely correct.
English
Elon, there’s a lot of people saying SpaceX is deprioritizing Mars this Earth-Mars launch window and focusing on the moon instead. I don’t really trust this, unless I hear it from the source.
Can you shed some insight on what the plan is?
Thanks!
English
Out now: Teams, aka. Agent Swarms in Claude Code
Team are experimental, and use a lot of tokens. See the docs for how to enable, and let us know what you think! code.claude.com/docs/en/agent-…
Lydia Hallie ✨@lydiahallie
Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!
English
Guinness with John & Dwarkesh 🍺
John Collison@collision
Please enjoy this Cheeky Pint / @dwarkesh_sp crossover with @elonmusk. Dwarkesh was most interested in how Elon is going to make space datacenters work. I was most interested in Elon's method for attacking hard technical problems, and why it hasn’t been replicated as much as you might expect. But we got into plenty of topics in this three-hour session. 00:00:23 Space GPUs 00:35:39 Alignment 00:58:48 xAI 01:15:01 Optimus 01:28:03 China 01:40:46 Management 02:16:38 DOGE 02:34:58 Space GPUs redux
English
@PerceptualPeak Unrelated but have you guys tried the sneak peek yet? github.com/mikekelly/clau… once cloned you call it with claudesp. It does not connect to whatever claude you have its seperate fyi so semantic stuff you are doing none of that will be there. It has teammate mode highly recommend
English
CLAUDE CODE IDEA: I have absolutely NO idea if this is feasible or even practical...but I've been trying to think of some potential solutions to the massive amount of tokens consumption that happens when a session explores a codebase to get the current state of a project.
So WHAT IF....you chunked and embedded every single project codebase in a vector database? And set up an automation that would re-chunk/embed each time it gets updated?
And instead of Claude wasting 100k tokens exploring the raw codebase, it only uses say, 25k tokens by embedding recall - using a subagent to intelligently generate & embed queries to retrieve ONLY what it needs from the codebase?
Has anyone ever tried something like this?? Think I might experiment with this idea...
English
NASA used Claude Code to plot and simulate the Perseverance rover’s route on Mars 👾
Pretty sure this is the furthest-from-Earth application of Claude
Anthropic@AnthropicAI
On December 8, the Perseverance rover safely trundled across the surface of Mars. This was the first AI-planned drive on another planet. And it was planned by Claude.
English
"ClawdBot is nothing special. ChatGPT can do all of this"
OK, if you can show me how ChatGPT does the following use cases I've accomplished, I'll write you a check for a million dollars:
• Every night vibe codes me new tooling without me asking
• Self improves itself by building new memory systems. Now remembers every detail of every conversation (again, without me asking)
• Texts me proactively when a competitor posts a Youtube video that performs better than their average
• Continuously analyzing my own youtube videos, writing new scripts based on structures and hooks that work. Delivers a new script to my inbox every morning (one video it scripted already has $2,600 of ad revenue)
If you can show me how to do any of these use cases with ChatGPT without any additional tooling, the million dollars is yours.
English
CRITICAL: EVERYONE USING CLAWDBOT SHOULD RUN THIS PROMPT RIGHT NOW:
By default, the 2 best Clawd memory features are turned OFF
Running this 1 prompt will immediately stop your AI from getting confused in between compactions/sessions:
Prompt:
"Enable memory flush before compaction and session memory search in my Clawdbot config. Set `compaction.memoryFlush.enabled` to true and set `memorySearch.experimental.sessionMemory` to true with sources including both memory and sessions. Apply the config changes."
Here's what you enabled by running that prompt:
Memory Flush: Your AI automatically saves everything important to a file right before its context gets wiped, so nothing slips through the cracks.
Session memory search: Your AI can search through every conversation it's ever had with you, even ones it no longer "remembers."
Boom, your ClawdBot memory is now 10000x better
English
@PerceptualPeak github.com/Spacehunterz/E… I upgraded my project and gave you credit for memory. Not exact copy, but very useful implementation no doubt!
English
I created a repo for my semantic memory system (with both UserPromptSubmit & PreToolUse hook configuration).
Enjoy! If anyone has any issues getting it going let me know!
REPO: github.com/zacdcook/claud…
Zac@PerceptualPeak
WOW!!! If you have semantic memory tied to your UserPromptSubmit hooks, you MUST ALSO include it in your PreToolUse hook. I promise you - it will be an absolute GAME CHANGER. It will put your efficiency levels are over 9,000 (*vegeta voice*). How many times have you sat there, watching Claude code go through an extended workflow, just to notice it start to go down a path you just KNOW will be error filled - and subsequently take it forever to FINALLY figure it out? The problem with relying strictly on the UserPromptSubmit hook for semantic memory injection is the workflow drift from your original prompt. The memories it injects at the initiation of your prompt will be less and less relevant to the workflow the longer the workflow is. Claude has a beautiful thing called thinking blocks. These blocks are ripe for the picking - filled with meaning & intent - which is perfect for cosign similarly recall. Claude thinks to itself, "hmm, okay I'm going to do this because of this", then starts to engage the tool of its choice, and BOOM: PreToolUse hook fires, takes the last 1,500 characters from the most recent thinking block from the active transcript, embeds it, pulls relevant memories from your vector database, and injects them to claude right before it starts using its tool (hooks are synchronous). This all happens in less than 500 milliseconds. The result? A self correcting Claude workflow. Based on my testing thus far, this is one of the most consequential additions to my context management system I've implemented yet. Photos: ASCII chart showing the workflow of the hook, and then two real use-cases of the mid-stream memory embedding actually being useful. If you already have semantic memory setup, just paste this tweet and photos into Claude code and tell it to implement it for you. Then enjoy the massive increase of workflow efficiency :)
English
@steipete @NetworkChuck @openclaw Everyone knows the name is irrelevant. Could have named it shithead, and people would still be flocking to it.
English
@NetworkChuck @openclaw try picking a name without sleep and a gun at your head 🙃
English
...@openclaw .....really?
Dude, reach out to me next time for some branding help.
But still better than clawdbot.
English
Congrats to the @Neuralink team for helping many people who have lost use of their body with our Telepathy implant that enables computer use simply by thinking!
The next generation Neuralink cybernetic augment with 3X capability will be ready later this year.
Pending regulatory approval, we are also ready to do our first Blindsight augment that will enable those who have even complete loss of vision to see in low resolution at first, leading to high resolution over time.
Neuralink@neuralink
We now have 21 participants enrolled in trials worldwide. Check out how our Neuralnauts are driving BCI technology forward. neuralink.com/updates/two-ye…
English
WOW!!! If you have semantic memory tied to your UserPromptSubmit hooks, you MUST ALSO include it in your PreToolUse hook. I promise you - it will be an absolute GAME CHANGER. It will put your efficiency levels are over 9,000 (*vegeta voice*).
How many times have you sat there, watching Claude code go through an extended workflow, just to notice it start to go down a path you just KNOW will be error filled - and subsequently take it forever to FINALLY figure it out?
The problem with relying strictly on the UserPromptSubmit hook for semantic memory injection is the workflow drift from your original prompt. The memories it injects at the initiation of your prompt will be less and less relevant to the workflow the longer the workflow is.
Claude has a beautiful thing called thinking blocks. These blocks are ripe for the picking - filled with meaning & intent - which is perfect for cosign similarly recall. Claude thinks to itself, "hmm, okay I'm going to do this because of this", then starts to engage the tool of its choice, and BOOM:
PreToolUse hook fires, takes the last 1,500 characters from the most recent thinking block from the active transcript, embeds it, pulls relevant memories from your vector database, and injects them to claude right before it starts using its tool (hooks are synchronous). This all happens in less than 500 milliseconds.
The result?
A self correcting Claude workflow.
Based on my testing thus far, this is one of the most consequential additions to my context management system I've implemented yet.
Photos: ASCII chart showing the workflow of the hook, and then two real use-cases of the mid-stream memory embedding actually being useful.
If you already have semantic memory setup, just paste this tweet and photos into Claude code and tell it to implement it for you. Then enjoy the massive increase of workflow efficiency :)
English
In the next version of Claude Code, you can customize spinner verbs for yourself and your team
English
@ZachAI had to come back to say huggingface.co/Qwen/Qwen3-TTS… its blazing fast!
English
@josh_ladner I bet there’s some faster TTS options if you look around! and yeah responses can get very long so that’s tricky, maybe use another model to summarize responses & takeaways?
English
building with AI tips thread
x.com/zach_is_cookin…
zach@ZachAI
claude code tip: have it make a sound when it needs your input use the hooks in ~/.claude/settings.json to trigger a sound. terminal-notifier works well for this. just give your terminal notification permission and you're good to go
English
claude code's new task system is soooo good.
total game changer for multi-agent work.
agent swarms that *actually* work are coming soon.
English
The Adolescence of Technology: an essay on the risks posed by powerful AI to national security, economies and democracy—and how we can defend against them: darioamodei.com/essay/the-adol…
English
English
I'm working on LINE integration and it's now the 10th time I use /review and each time it did find a valid, tricky bug. Getting sessions right and all the mapping between agents is finicky and each time I'm refactoring and cleaning up code. There gotta be a better way.
English
@NicerInPerson If you want to expand on it I had this working before it was released also thank you for the pack! github.com/Spacehunterz/E…
English
I managed to unlock a crazy new hidden feature in Claude Code called Swarms. You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. When you approve a plan, it enters a new "delegation mode" and spawns a team of specialists who:
- Share a task board with dependencies
- Work in parallel as teammates
- Message each other to coordinate work
Workers do the heavy lifting, coordinate amongst themselves, then report back.
English
Just to see what would happen I texted Henry my Clawdbot to make a reservation for me next Saturday at a restaurant
When the OpenTable res didn't work, it used it's ElevenLabs skill to call the restaurant and complete the reservation
AGI is here and 99% of people have no clue
English