jp

2.3K posts

jp

jp

@jonathanprozzi

eng working on ai, coordination, and networked thought

Katılım Haziran 2013
2.1K Takip Edilen5.2K Takipçiler
jp
jp@jonathanprozzi·
@LLMJunky very cool! sharing with my friends who use linux and have been wanting to check out a codex desktop app!
English
0
0
1
21
am.will
am.will@LLMJunky·
What are you doing to achieve your /goals today? GOALS available on the Codex App for Linux now Link in the comments!
am.will tweet media
English
13
7
69
5.3K
jp
jp@jonathanprozzi·
@RhysSullivan I've been using it for shorter, cleanly scoped runs. I create a well defined plan/objective and then build via passing it into `/goal` runs
English
0
0
0
487
Rhys
Rhys@RhysSullivan·
what are you guys using /goal for? i haven't tried it yet but i can't imagine letting the agent run for 12+ hours produces code that's anywhere near shippable
English
111
4
310
51.6K
jp
jp@jonathanprozzi·
@LLMJunky Fall (Oct-Nov 2022) but didn't really dive in until early Spring 2023!
English
1
0
1
56
am.will
am.will@LLMJunky·
How long have you been in AI? Where the OGs at? 👇
English
57
0
46
7.7K
jp
jp@jonathanprozzi·
@Mappletons personal ones (no intent to publish and are global to my workflows) in my dotfiles personal public ones in an agent-skills repo team specific, internal ones in a team skills repo team skills intended to publish in an org agent-skills repo then i use symlinks from these sources
English
0
0
1
1K
Maggie Appleton
Maggie Appleton@Mappletons·
How is everyone managing their agent SKILL.md files? Is it just chaos? Global skills, repo-specific skills, keeping them in sync between machines, figuring out which ones you have installed, authoring new ones. What are we doing? Does anyone have a sane system?
English
233
13
688
105.6K
jp retweetledi
Vercel
Vercel@vercel·
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/ve…
English
698
2.4K
8.8K
10.6M
jp retweetledi
Addy Osmani
Addy Osmani@addyosmani·
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.
Lenny Rachitsky@lennysan

"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

English
85
93
686
168.5K
jp
jp@jonathanprozzi·
@W00DS_eth @h0xrus Also thank you for your kind words 🫶
English
0
0
3
25
jp
jp@jonathanprozzi·
@W00DS_eth @h0xrus Agreed! Such a great space. @h0xrus covered so many awesome topics. Stoked for this collaboration!
English
1
0
3
27
jp
jp@jonathanprozzi·
@dexhorthy @DanielleFong made similar decision earlier too - been sticking to the 40% since I read your article about it awhile back!
English
0
0
1
175
dex
dex@dexhorthy·
Adding opus 1m support meant we revised the context warning in humanlayer from “40%” to “100k tokens”
Matt Pocock@mattpocockuk

Doing some experiments today with Opus 4.6's 1M context window. Trying to push coding sessions deep into what I would consider the 'dumb zone' of SOTA models: >100K tokens. The drop-off in quality is really noticeable. Dumber decisions, worse code, worse instruction-following. Don't treat 1M context window any differently. It's still 100K of smart, and 900K of dumb.

English
12
4
81
20.9K
W 0 0 D S
W 0 0 D S@W00DS_eth·
This is the best way to use Claude Code... I've been using Claude with Obsidian since December and my AI workflow has gotten 10x better from this alone. The longer you use this setup, the more powerful it becomes as you expand the memory knowledge graph. DO THIS TODAY
GREG ISENBERG@gregisenberg

claude code + obsidian in under 1 minute

English
4
0
19
777
jp
jp@jonathanprozzi·
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
banteg@banteg

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.

English
0
0
6
132
jp
jp@jonathanprozzi·
so stoked to try this! observational memory is extremely powerful already love @mastra and the team keeps shipping even more amazing features!
Tyler Barnes@tylbar

🚨 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 🧵

English
1
0
5
170
jp
jp@jonathanprozzi·
@banteg I’ve been having this happen even at low context usage percents later in session. I’ll proactively compact and still see it. It’s very odd. I close the session and start from a log or summary or try to rewind to a recoverable step.
English
0
0
1
212
banteg
banteg@banteg·
what am i supposed to do with this? seems an unrecoverable state in claude.
banteg tweet media
English
45
1
89
25.3K
jp
jp@jonathanprozzi·
@NickMilo completely agree. I loved obsidian before integrating directly into my workflow and now I love it 100x more. True operating system for the agentic era imo
English
0
0
3
761
Nick Milo
Nick Milo@NickMilo·
Obsidian has officially won the note wars. Everyone seems to be scrambling to install complex protocols, paying for plugins or built-in AI subscriptions—or just switching apps once again—as their current app fails to catch up to the latest AI developments. Meanwhile, over in Obsidian, AI integration looks like this: Point AI at a folder. And you're done. Or, if you're like many reading this, don't integrate AI at all. Either way, with Obsidian, it's your choice. Link to the vid below in the comments 👇
Nick Milo tweet media
English
49
26
487
111K
jp
jp@jonathanprozzi·
@trq212 this is awesome! stoked to dive in and explore Opus 4.6 further
English
0
0
1
713
Thariq
Thariq@trq212·
These are the videos I made with Opus 4.6 using Remotion. It helped me brainstorm & script them, translate our design system into react components and even generated and inserted the sounds using the elevenlabs APIs. I never looked or edited at a single line of the code.
English
40
24
533
39.9K
Thariq
Thariq@trq212·
Opus 4.6 is a special model, it really feels like a true collaborator you might have got a sneak peek at its work earlier this week- the videos I launched were made completely by Opus 4.6 (see below)
Claude@claudeai

Introducing Claude Opus 4.6. Our smartest model got an upgrade. Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes. It’s also our first Opus-class model with 1M token context in beta.

English
46
26
775
72.5K
jp
jp@jonathanprozzi·
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!
jp tweet media
English
0
0
1
105
jp
jp@jonathanprozzi·
@calcsam congrats! I’ve enjoyed building with Mastra since I first used it and y’all just keep shipping 🔥
English
1
0
2
101
jp
jp@jonathanprozzi·
@AlexTamkin i absolutely love this new feature and see so much potential for self-reflection and also improving how teams/fellow collaborators have our workflows evolve over time
English
1
0
2
451
jp
jp@jonathanprozzi·
@trq212 this is one of my favorite new features that you've added recently i love how much claude is able to glean from our sessions and is always geared toward improving workflows and collaboration
English
0
0
1
655
Thariq
Thariq@trq212·
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.
English
501
656
11.6K
1.2M

Keşfet

@LLMJunky @RhysSullivan @Mappletons @W00DS_eth @h0xrus @dexhorthy @DanielleFong @elonmusk