Leading AI practices. Agentic network engineering https://xitter.cf/t.co/j0Gu0Qq4RZ Systems not the prompts https://xitter.cf/t.co/a2Ram1Rarv

MD
Joined November 2015
How I do Agents to do my work in cursor or claude.
5
749
The things we can do with AI. I mean the shit I'm working on now..
2
73
These are good, but you have to maintain struct enforcement of the sub task running or they will drain your tokens pretty fast if you aren't paying attention to what they are there for.
Boris Cherny, Head of Claude Code at Anthropic, just shared an official tip before Fable 5.5 ships The setup: split your workload across Opus 5.5, Sonnet 5.5, and Haiku 5.5, and let them talk directly across your open terminals Zero context pollution between windows: independent sessions ping each other via plain-text IPC over local sockets without burning a single token on conversation history You just launch Claude Code like this: claude --model sonnet --settings '{"crossSessionInbound":"accept"}' here's the split: → Opus 5.5 architects session permissions: audits ListAgents discovery, enforces inbound message policies, and signs off on multi-terminal diffs → Sonnet 5.5 executes code fixes: builds endpoints, updates schemas, and patches dependent code whenever a peer session reports a breaking change → Haiku 5.5 relays inter-session messages: processes SendMessage pings across terminals at 340 tok/s with zero history bloat and sub-millisecond local socket latency → you stop burning Opus context on manual copy-pasting between terminals and keep your sessions lean Opus only steps in at three moments: → setting up cross-session topology and inbound security rules before launch → evaluating contract diffs when a peer message signals an API schema update → signing off on synchronized multi-session PRs before merging to main Opus architects · Haiku relays · Sonnet executes JEV engineering is the same move one layer down: the forks that need no thinker (which peer, which tool, forward or drop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 architects session permissions and audits cross-session topology > Haiku 5.5 relays SendMessage pings between terminals at 340 tok/s > Sonnet 5.5 patches code across workspaces when a peer signals a change > Sessions discover each other automatically via ListAgents and /peers > Messages travel as isolated plain text over local IPC sockets with 0 context dump > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Configure cross-session discovery using /peers and set crossSessionInbound to accept 2. Delegate all peer-to-peer message routing and notification triage to Haiku 5.5 at 340 tok/s 3. Spawn Sonnet 5.5 to execute code edits and synchronize types whenever a peer session reports an update 4. Restrict all cross-session payload traffic to lightweight plain text via SendMessage with zero history transfer 5. Reserve Opus 5.5 for inter-session capability authorization and final sign-off before committing Show me every change as a diff first. No edits until I say go" ↳ code.claude.com/docs/en/cros… bookmark this, your terminals now talk to each other
102
Decided to create a new one. youtube.com/@deirradecoded
Ill record a more in depth video this week. Lemme dust off my YouTube 🤣
3
4
1,506
Yes you see bullshit much faster, failures in people's POV, because it broke one of the laws of a science/
Did learning algebra, physics and chemistry ever actually come in handy in your adult life?
66
End of an Era.
BREAKING: BioWare, makers of Knights of the Old Republic, Baldur's Gate and Mass Effect, is closing.
1
1
80
Here are the basic rules when you are trying to build out your agentic practice starting at the harness. Get your team using less tokens. Here is a good place to get started building agents. claude.ai/artifact/6Gj2PrWBC…
1
68
My findings from working on building a practice is most teams are using AI in some capacity, but the skill level is not where it needs for most people to take advantage of it. I'll be sharing some solutions
1
86
All those things are true...However He has an above average talent of staying in the pocket when he raps. That just gonna draw attention. Then combine it with the gluttony of his lifestyle and there is your answer
My view: Rick Ross violates every hip hop rule. He stole his name, made up a persona, poisons the youth and is not even special as a rapper. His lyrics are simple, stimulate useless consumerism and have monotone subject matter. Why should anybody even listen to this clown?
97
yes i played too much
If you played Age of Empires II or WoW as a kid, I'd lowkey trust you with my life. You were running economies and raid groups at f*cking 12 years old.
129
Even thought I do most of my work on claude just cause I built all my tooling there. CURSOR is still the best Value at 60 a month if you haven't committed to anything yet.
1
122
Building out a lot of the practice on Agent Core in AWS. I actually enjoy that the majority of the tooling is right there.
73
The situation in Ethiopia has a lot of potential to get out of control.
75
As much as I like making beats. I actually really enjoy making tooling for creators like BPM match tools, groove tools, sample finders etc. I find that work prettty intresting and AI allows me to make them pretty fast
76
My AI record agent is one of the best things I've built with AI that can go out and find samples for me according to my taste.
2
1
4
220
My AI record agent is one of the best things I've built with AI that can go out and find samples for me according to my taste.
2
1
4
220
Joe Rogan: “Trump supporters are f*cking nuts, man. They’re rabid.”
36
2,166
32
13,850
541,740
I'm going to have to get into AI security cause nobody else is gonna do it. 🤣
2
1
2
8
1,079
You can't change the past you have the present moment. You can't worry about the future you have the present moment. Best thing I learned from sports from a bad round etc. You have the next moment.
Something I noticed about resilient people: They don't have fewer problems. They have faster reset times. Bad news hits at 9am. By 10am, they're back to their priorities. They feel it, process it, and move. The speed of the reset matters more than the size of the setback.
1
147
I'm going to have to get into AI security cause nobody else is gonna do it. 🤣
2
1
2
8
1,079
So what they said is they got AI agents to run game theory with the variables they made to test the date out. Go make your own copy.
JUST IN: Dating startup Ditto launches AI agents that go on “simulated dates” with hundreds of other users’ agents to find compatibility before recommending real-life matches.
2
132