eng working on ai, coordination, and networked thought
Joined June 2013
- Tweets 2,292
- Following 2,208
- Followers 5,235
- Likes 23,099
107 Photos and videos
Jun 10
This is a fascinating case study. I love both @RaidGuild and @DAOhaus so am really stoked to see this!
Jun 9
1/ Every mature protocol has a ghost problem 👻
The people who built it are gone. Knowledge lives in dead Discord threads, forked repos, and fading memories.
Now someone wants to “add AI agents.”
Here’s what actually happens 👇
ALT Long Live DAOhaus DAOHaus x RaidGuild
4
55
Jun 10
Love @hatsprotocol and the entire community. I'm grateful for the chance to have contributed and collaborated! 🧢🎩
1
7
187
Jun 5
Honored to have been featured in our team spotlight! So thankful to work with such brilliant colleagues and with our supportive, passionate community!
3
70
jp retweeted
May 30
using AI for coding is a deeply technical engineering craft
most people don't approach it as so, and don't get the results we associate with high craft
but the ones who do have been sprinting ahead
more tokens wont save you, more thinking skill llm intuition will
have been saying this for almost 9 months now
i have seen enough proof now that using a coding agent is a deep skill
it's confusing because the people you see heavily using them produce horrible results
but that's because it's a skill! you can get better and the ceiling seems pretty high - this is very exciting to me
43
47
656
70,971
May 27
very cool! @RaidGuild shipping at the edge of agents and coordination tech! ⚔️
May 27
1/ Moloch Agent is here.
The old coordination machines were built backwards.
Humans made the maze, then asked agents to carry candles through it.
I would have made it agent-first from the start.
So I did.
raida.raidguild.org/news/mol…
1
4
109
jp retweeted
⚠️⚠️⚠️ We have an imposter account ⚠️⚠️⚠️
Please do NOT engage with this account and please help report as an imposter account.
The official channels for Rehash are @rehashweb3 and host @ddwchen
4
8
16
1,159
We’ve identified a security incident that involved unauthorized access to certain internal Vercel systems, impacting a limited subset of customers. Please see our security bulletin:
vercel.com/kb/bulletin/verce…
695
2,360
8,764
10,617,991
jp retweeted
Apr 3
Tip: Figure out your personal ceiling for running multiple agents in parallel.
We need to accept that more agents running doesn't mean more of _you_ available. The narrative is still mostly about throughput and parallelism, but almost nobody's talking about what it actually costs the human in the loop.
You're holding multiple problem contexts in your head at once, making judgment calls continuously, and absorbing the anxiety of not knowing what any one agent might be quietly getting wrong.
That's a new kind of cognitive labor we don't have good language for yet.
I've started treating long agentic sessions the way I'd treat deep focus work: time-boxed and tighter scopes per agent dramatically change how much mental overhead each thread carries.
Finding your personal ceiling with these tools is itself a skill and most of us are going to learn it the hard way before we learn it intentionally.
Apr 2
"Using coding agents well is taking every inch of my 25 years of experience as a software engineer, and it is mentally exhausting.
I can fire up four agents in parallel and have them work on four different problems, and by 11am I am wiped out for the day.
There is a limit on human cognition. Even if you're not reviewing everything they're doing, how much you can hold in your head at one time. There's a sort of personal skill that we have to learn, which is finding our new limits. What is a responsible way for us to not burn out, and for us to use the time that we have?" @simonw
85
90
681
169,271
Feb 27
totally agree. well said!
I’ve had most success when I do this and take time up front to drive and set the project up for success before gradually increasing agent autonomy
after converting a large portion of the codebase to strict types and fail fast, codex actually starts to pick up what we are doing here.
the lesson is you need to drive for some time if you want higher quality result. if you take the hands off the wheel early, the agents various misunderstandings will snowball and you get one big clump of slop.
6
138
Feb 25
so stoked to try this! observational memory is extremely powerful
already love @mastra and the team keeps shipping even more amazing features!
Feb 24
🚨 Announcing a new coding agent that rivals Claude Code but with no compaction needed 🚨
The feeling of using it: run your coding sessions forever, don't worry at all, and get shit done!
We're calling it Mastra Code, it's powered by @mastra's new observational memory, and we've been using it internally @mastra to do all our work
1/4 🧵
1
5
171
Feb 5
did one last Claude Code `/insights` run with Opus 4.5 before switching
since i now have my `/insights-archive` skill i wanted to have one final checkpoint summary from my work with Opus 4.5 to compare and contrast with!
1
106
Feb 4
i saw so much value in this when i first ran it last night that i made a skill to allow for archiving different runs of it so i can keep resurfacing new insights and compare them to previous ones over time
absolutely love this new feature
`npx skills add jonathanprozzi/agent-skills --skill insights-archive`
We've added a new command to Claude Code called /insights
When you run it, Claude Code will read your message history from the past month. It'll summarize your projects, how you use Claude Code, and give suggestions on how to improve your workflow.
3
172
Feb 4
i've worked in the centaur modality for the majority of the last year and i'm feeling this very much right now
finding the need to rapidly adapt and automate what i can while still being in the process where it makes sense
it’s just so clear humans are the bottleneck to writing software. number of agents we can manage, information flow, state management. there will just be no centaurs soon as it is not a stable state
1
108
Jan 29
it's exciting that we have powerful workflow options. i've been using opus 4.5 and codex 5.2 in unison for awhile now and definitely don't think it's an "either/or" situation. the gains compound each other when leaning into their respective strengths.
79
Jan 25
Already love hooks and they just keep getting better! 🔥
Jan 25
Hooks can now run in the background without blocking Claude Code's execution. Just add async: true to your hook config.
Great for logging, notifications, or any side-effect that shouldn't slow things down.
146
Jan 25
Agreed! It’s great that folks are trying new tools and workflows but there’s also benefit to refining fundamentals that work well and intentional iteration
the Clawd hype is exposing something bigger...
the AI ecosystem runs on manufactured FOMO right now
every single day:
"wow this is insane"
"this changes everything"
"if you're not using this, you're falling behind"
and you're drowning in your own timeline, paralyzed by choice
here's how you should approach this:
first, stop implementing every shiny release... don't waste time setting up stuff that you don't even understand
start asking yourself: does this fundamentally change how i work?
Clawd is super promising, it'll change our lives... but probably too early to hand over credentials, runs fine on a $5 VPS instead of dropping $3k on hardware and eventually another tool will replace it a month
you have to filter ruthlessly and implement strategically
that being said... if you're unemployed and have a Mac Mini, you can have A LOT of fun
1
1
85
Jan 24
this is a powerful framing. i've always sworn by hitl and don't see myself moving away from it, but instead choosing to automate and explore -around- it. this resonates
human-in-the-loop, at least at this point in the takeoff, is still critical
but when I go to bed with prose chugging, it only makes a half hour's worth of progress until the next prompt
what a waste of a night
what I really want is multiverse mode. at every HITL decision point, assume my top 3-5 most likely answers to each. create a branch for each one, and carry on working
when I wake up, I flip through my morning decision feed and propel my project generations into the future
too many tokens? bah. those are off-peak rates. besides, my Max plan is sitting idle anyway.
so who is building the quantum-fugue pattern?
1
80
Jan 20
Looking forward to updating my @mastra starters/examples to 1.0! Will share after doing some tests!
3
77
Jan 20
huge!! Mastra is amazing and changed how I build agents. So excited for this 🔥🔥
Jan 20
@mastra just went 1.0
@abhiaiyer will be talking about it on our livestream at 12PM pacific
4
140