building @humanlayer_dev, YC alum, @aitinkerers sf lead, prev @replicatedhq @SproutSocial @nasa ai that works pod @ hlyr.dev/aitw
San Francisco, CA
- Tweets 8,128
- Following 2,018
- Followers 52,874
- Likes 13,226
Pinned Tweet
coming soon to a humanlayer new you:
live multiplayer prompting - co-author a single prompt with your team.
A few weeks ago we shipped "send a prompt to your colleague's session" - now we made each individual prompt collaborative.
No cloud agents required, works wherever you run your agent - across laptops, mac minis, cloud compute, we even have this working in coding agent sessions that run in disposable compute like github actions.
built on durable streams and @rivet_dev actors on ECS - incredible work from @0xblacklight
That's in addition to all the other things we made collaborative in the last 2 months:
- live google-docs style commenting on plans, right in the IDE, or plan/collab from your phone
- diffs stream live as the coding agent is working, so you can comment on changes wayyy before PR
shift collaboration left, shift alignment left, go check it out @humanlayer_dev - free for small teams go check it out today
28
11
158
40,715
crazy new drop - you can now use humanlayer directly from Pi agent or @opencode - bring your harness, use it how you like, and make every session collaborative and remote-controllable!
4
4
50
3,256
dex retweeted
Super fun chatting with @vaibcode @dex about how we replaced BI with AI Agents we built in GrowthOS at Rippling
piped.video/bGMiRmXbRUs?is=ukic…
2
2
14
5,368
sent my claude code to configure a Dots for me overnight with computer user (importing our markdown crm and daily/weekly SOPs) and the two agents immediately started a good deal of posturing. delightful
16
71
9,114
wow so i have built like 10 integrations on "GitHub Apps" since it launched in 2018 as an alternative to oauth. I have probably used over 100
none of them was harder to get to the "configure connected repos" than going through chatgpt web to try to connect this to my dot (mind you, this is a page HOSTED ON GITHUB, the provider just needs to link to it)
13
1
37
7,577
damn so i know i never did the "9 video games" thing but this should give you all the information you need 🤣
Made w/ Opus 5.5 and a whole lot of fiddling with @ElevenLabs
been a little quiet lately but excited to share what's next: HumanLayer is building the software forge for AI and whatever comes after it
6
3
86
14,376
great post from @exedev team - the same thing that has always been true of software engineering is still true:
Do fewer things in parallel, do them very well, optimize for getting incremental value out to users, FOCUS
It's been 30 years since the XP and Lean folks said "limit work in progress (50+ if you count the eli goldratt thing) - its still true
blog.exe.dev/etoomanythings
23
34
574
26,497
yet another deeply unsaturated benchmark on model’s ability to maintain a codebase
Can LMs discover & fix bugs if you don't tell them what went wrong? To proactively maintain a repo, agents need to find problems before users do.
SWE-sweep benchmarks this on 100 repos, 22 languages, 4k real bugs (numpy, php interpreter, lean kernel). Top models get <5%.
22
15
451
43,019
this guy gets it
on ai psychosis:
as i watch engineers fall deeper into the belief that an amalgamation of mathematical probabilities somehow understands their codebase better than they do, i find myself thinking back to a time when software wasn’t built for hypergrowth, but simply to do x without inventing y.
ai seems almost fundamentally opposed to this philosophy. ask it to do x and it will eagerly invent y and z before it has even tried to understand x.
the danger isn’t that ai writes bad code- it’s that it makes writing unnecessary code 100% free
and the human condition is such that some of us will always prefer the fast, steep gains of ai, even when it does a bajillion unrelated things to accomplish something that could have been done without changing anything else.
so, somewhat paradoxically, the quality of software may keep declining for as long as ai keeps getting better. the cheaper complexity becomes to create, the less incentive there is to understand or avoid it.
try to preserve this craft created by our ancestors
write a LOC by hand today
13
5
253
99,765
live at the @EffectTS_ meetup in sf with @esthor @MichaelArnaldi @thefubhy @RhysSullivan @kitlangton @andrelandgraf and the vibes are absolutely immaculate
5
5
116
11,031
okay but hear me out @0xblacklight you should call our cloud agents feature “hogs”
Working on better orb memory management.
Opus 5.5 decided to call processes that take up a lot of memory "hogs"
Hogs!
Absolutely Right, Belt & Braces (& Suspenders), Goblins, and now it's Hogs?
5
21
8,383