yelling into void building a company
ex:
- api and search at @openai
- datacommons, spanner db at @google
- kernel hacker
gh: https://t.co/FoxgvqQGkwshanth.me Campbell, CAJoined August 2009
I think most people multi-tasking with agents could benefit from slowing down
most of the stuff you're doing wont really matter- what's your P0? what would it look like if you gave it your full attention?
cannot agree more
just want help on basic stupid shit like pull out details from the screenshot my dad texted me last month and plug them into the web form am filling now
there are so many everyday demos that could make ai, personal agents, & agents in general feel insanely powerful to normal ppl & yet ai companies keep choosing things like booking flights, planning travel, or god forbid planning a god damn wedding.
these are not everyday
codex desktop app has been a bit buggy lately
like
- the app hung on me a few times had to hard kill
- even after completion the last tool call may remain flickering with `Running`
- not able to move threads in a project in the left panel
devday collateral damage? 😅
think i've got enough llm intelligence for now, its only cost and readability at this point
a few more jev like oom jumps for specific tasks would be nice though
i now care way less about incremental intelligence increases and a way lot more about *any* readability improvements so this is good
if english is the code it better effin not be so off-putting to read
Opus 5.5 communicates more naturally, addressing some of the most common feedback we heard on Opus 5.
It puts the most important information up front and follows the writing rules you give it, which makes long sessions easier to follow.
Opus 5.5 communicates more naturally, addressing some of the most common feedback we heard on Opus 5.
It puts the most important information up front and follows the writing rules you give it, which makes long sessions easier to follow.
plugin install in claude desktop is so confusing
there are separate installs for code vs cowork, the interfaces look deceptively similar, and if you install in the code side connectors are accessible in cowork but not the skills
Maybe you have recently become aware of the AI safety debate and the arguments swirling around it.
If you want to understand them, you need to understand a couple things that almost everyone gets wrong:
There are TWO distinct classes of AI dangers, and it's VERY important to
Introducing Conductor Cloud!
Out with worktrees, in with multiplayer cloud workspaces.
Bring your subscriptions, invite your teammates, start your agents, and shut your laptop. Conduct from iPhone and API, too.
conductor.build
3K Followers 1K FollowingPhD - Royal College of Music, London; MA - Univ. of East Anglia; B. Tech - NIT, Trichy. Researching audience experience, audiovisual culture, video essays.
99K Followers 913 FollowingCreator of Flask. Building at https://t.co/uGuzfu0LKT. Bypassing Permissions. Can hand crank. Husband and father of 3 — “more nuanced in person”
65K Followers 2K Followingbuilding https://t.co/gIFOwRUrLU - the cloud for personal software. connect all your integrations once, use them with any agent | yc 26
6K Followers 5K Followingfounder @puma_ai, angel investor
prev. dev rel at Meta (Parse), @Meteorjs, Cloudant
grew up in 🇺🇦🇯🇵🇨🇦
6’4”, enjoy travel, tennis and photos 🌁🎾📷
50K Followers 4K Followingplaying with words. creating whimsical ai @ https://t.co/khnCIspDsd. built iOS apps @xAI, @Spotify, and co-founded @imagilabs.
50K Followers 61 FollowingI've been in the industry for O(40) years and have written O(1M) LOC. I don't think I'll ever write O(another) line again, but I'll be launching more than ever.
13K Followers 345 FollowingCCO @Anthropicai. Enterprise AI adoption at scale is what I think about most. Previously commercial leadership at ServiceNow, Salesforce, Microsoft.