Louis

11.6K posts

Louis banner
Louis

Louis

@SickBots

idk @humanlayer_dev

San Francisco, CA Sumali Aralık 2012
324 Sinusundan737 Mga Tagasunod
Louis
Louis@SickBots·
Yep, still doing 12 hour workdays.
English
0
0
0
14
Louis
Louis@SickBots·
Can I stop w/ the 12 hour work days or no
English
1
0
1
81
Louis
Louis@SickBots·
I’m about to study/grind until she texts me
English
1
0
2
148
Louis
Louis@SickBots·
codex 5.3 for one-liners, opus 4.5/4.6 for pretty much everything else
English
0
0
0
30
Louis
Louis@SickBots·
using opus 4.7 atm strictly only gathering research
English
1
0
0
26
Louis nag-retweet
dex
dex@dexhorthy·
have started doing some switch-hitting between claude and codex ever since we rolled our own alternative harness in march. Opus 4.7 now available in humanlayer ofc. Recent vibes: - opus 4.5 more reliable than 4.6 or 4.7 for most things. (fwiw i actually preferred intelligence of 4.1 to 4.5 but 4.5 is so much faster that its worth the tradeoff) - 1m context is useful for some cases but i still try to stay under 100k tokens for serious work on our large monorepo by externalizing task progress to MDs - codex takes more time to review and research code before - this means it needs less intentional steering to research and planning, it can tackle bigger things with just a simple prompt - codex takes more time, this makes it slower, which can be annoying if you are used to claude just getting to work - codex, esp 5.4 is less trigger-happy than claude models, it is more likely to ask "want me to run the tests" or "want me to go make this change" vs. just going to do the thing. This actually makes afk yolo-ing harder. but if you are working off plans its fine. - claude code cli/sdk continues to add features, flag on random new things, we disable a lot like auto memory and adaptive thinking while working. In general the more built in tools and agents, the less room for your instructions. If you don't own the harness you're at the whims of what the model provider thinks you need to get better results. - this generally seems to be optimized for new users getting results, at the cost of giving flexibility to power users - the frontier is jagged and opus 4.7 is good at a few random things that prev models were not as good at (no spoilers! go poke around!) most people in the GC have been saying these things for weeks. but in case you were waiting to hear from me and @0xblacklight and team, here's what we got thanks @nayshins @GeoffreyHuntley @SickBots @nisten and many others for contributing to the vibe report
dex tweet media
English
9
11
92
10K
Louis nag-retweet
Srishti
Srishti@srishticodes·
Nearly entire Github dashboard is useless
Srishti tweet media
English
155
274
5.8K
243.5K
Louis nag-retweet
typedfemale
typedfemale@typedfemale·
presenting: big jeff's trainium hell
English
113
556
4.6K
635.8K
Louis nag-retweet
𝐑𝐔𝐁𝐄𝐍🥽𝐅𝐑𝐎
Been experimenting with procedural locomotion on #GaussianSplat environments from @theworldlabs . Built a little multi-legged robot in Unity that raycasts against the splat data to figure out where to place its feet, no meshes or colliders involved... Pretty fun to climb surfaces, walk on walls, and set a weird number of legs on the fly :) Still rough around the edges but pretty fun to watch it figure things out. #GaussianSplatting #Unity3D #WorldLabs #ProceduralAnimation
English
63
157
1.3K
144.1K
Louis
Louis@SickBots·
hm - claims to be as good as qwen3.5-122b.
Louis tweet media
English
0
0
0
40
Louis nag-retweet
Josh Cohenzadeh
Josh Cohenzadeh@jshchnz·
At the Agents Anonymous SF meetup last night we did another 🙋 AI usage survey, here are the est. numbers: Usage stats: - 90% Claude Code - 60% Codex - 30% Cursor - 20% OpenCode - 10% Conductor - 10% Own agent/Pi 80% have prompted a coding agent from mobile 50% have not handwritten a single line of code this year 99% think they're more productive now vs. pre agentic coding agents Parallel agent usage: - 90% 3+ - 70% 4+ - 50% 5+ - 5% 10 Also want to give a ginormous thank you to our incredible speaker lineup: - @jonas_nelle & @alexirobbins from @cursor_ai - @southpolesteve from @Cloudflare - @LewisJEllis from @ycombinator - @aidandcunniffe from Git AI - 🦞 @steipete from @openclaw Hope to see you all at the next one! 🫡
English
110
118
1.1K
172.8K
Louis nag-retweet
Heavybit
Heavybit@heavybit·
What's missing to make AI agents mainstream? For more perspective on putting agents into production for real-world engineering teams, we spoke with founder @dexhorthy of @humanlayer_dev. hubs.ly/Q047cLd80
Heavybit tweet media
English
0
3
5
5.9K
Louis
Louis@SickBots·
Imagine having both a girlfriend and a claude max subscription - what a dream
English
0
0
0
47
Louis nag-retweet
Kyle Mistele 🏴‍☠️
Kyle Mistele 🏴‍☠️@0xblacklight·
new blog post just dropped come get your excalidrawslop
Kyle Mistele 🏴‍☠️ tweet mediaKyle Mistele 🏴‍☠️ tweet media
English
7
7
59
8.2K
Anaya
Anaya@Anaya_sharma876·
Just installed Linux for the first time What’s the first thing I should install or set up ?
Anaya tweet media
English
755
103
2.6K
181.8K
Louis nag-retweet
Kyle Mistele 🏴‍☠️
Kyle Mistele 🏴‍☠️@0xblacklight·
where do you even get good frozen margs in the marina
English
0
1
1
529