harsh

1.3K posts

harsh

harsh

@HarshOnInternet

i build products and companies that solve problems for people. right now, turning AI tokens into shareholder value at https://t.co/JaVhi3IcrN

St. Louis Katılım Şubat 2011
702 Takip Edilen4.2K Takipçiler
@levelsio
@levelsio@levelsio·
Okay let's see who can reply to this
English
2.5K
17
2.2K
1M
Nat Eliason
Nat Eliason@nateliason·
@rachelgoodlad I have the “request alpha in your city” link always ready to go
English
1
0
3
129
harsh
harsh@HarshOnInternet·
@mert under all the vibecoded new launches looking for pmf is a gigantic ocean of already PMF companies automating everything by vibecoding we've automated 80%+ of our entire company at teslamr.com, all via vibecoding/agenting engineering whatever tf u wanna call it
English
0
0
1
66
mert
mert@mert·
so like has anyone actually gotten PMF with anything vibe coded so far or are we just gonna realize this was a huge bubble in a few months
English
301
27
1.5K
257.8K
harsh
harsh@HarshOnInternet·
@FurqanR Why not… Nebula?
English
0
0
2
175
Furqan Rydhan
Furqan Rydhan@FurqanR·
We're growing faster than we can ship content. Nebula needs a Dev Rel / Technical Content person who actually understands AI agents and can explain them like a friend. If that's you, DM me.
English
50
17
305
21.8K
harsh
harsh@HarshOnInternet·
big milestone for @xai... I've officially added grok 4.20 as the preferred model in production for a workflow over Anthropic, OpenAI and Gemini. little by little then all at once?
English
0
0
1
114
harsh
harsh@HarshOnInternet·
woah composer 2 is... fantastic and fast
English
1
0
2
127
Cathryn
Cathryn@cathrynlavery·
@Shaun__Furman sorry i meant 1 team, multiple agents but managed by a main orchestrator. I actually just reduced my team because there were too many agents, and I realized it just wasn't effective.
English
2
0
1
236
Cathryn
Cathryn@cathrynlavery·
🦞 pro-tip for multi-agent teams A big unlock for me with AI agent team is making agents report to my chief of staff, not me. Just added: → blockers go to him first, not my inbox → 9am + 4pm he surfaces what's stuck + one clear ask if he needs me on something → every escalation logs to autonomy-gaps.md Then I know where to fill in the gap so he needs me less and less.
English
12
2
69
5K
harsh
harsh@HarshOnInternet·
@ErikTrautman I have a codex 5.4 high instance on at all times in the openclaw folder and that’s made debugging a breeze. I urge you, keep going. My output has 100-1000x’d on all fronts of running a company… product, eng, marketing, content, ads, sales, literally everything.
English
0
0
1
58
erik
erik@ErikTrautman·
I'm very rusty, but the level of debugging I'm having to do with Open Claw just to get it to the starting line on a clean setup makes me skeptical of the tales of its easy successes.
English
5
0
3
579
harsh
harsh@HarshOnInternet·
happening more and more often. got more done in those 23m than an SEO agency I once paid $100k to over 6 months.
harsh tweet media
English
1
0
5
400
harsh
harsh@HarshOnInternet·
i feel like in an acquisition, our openclaw agent would arguably be worth more than the whole company
English
0
0
1
164
harsh
harsh@HarshOnInternet·
@onusoz 🙋‍♂️
QME
0
0
0
61
Onur Solmaz
Onur Solmaz@onusoz·
Request for beta-testers For a new stealth openclaw based project I am looking for companies that have deployed openclaw internally, but are bottlenecked by having just one agent for everyone on Slack, Discord, Teams, Mattermost, etc. If you qualify, please reply below or DM me
English
52
7
149
48.3K
harsh
harsh@HarshOnInternet·
routinely find myself saying things are 10x-100x faster/better/cheaper and it's not exaggeration
English
1
0
2
116
harsh
harsh@HarshOnInternet·
@gtmom @nateliason @mbateman 🙋‍♂️ soon :) got one more company to exit then I’m in (if ya’ll will have me)
English
2
0
7
203
harsh
harsh@HarshOnInternet·
@steipete what about as a daily driver in openclaw? tried it there yet?
English
0
0
0
169
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
it’s a good model. the coding specific jump is more in line what we had in 5.0 to 5.1; but it’s now unified and smarter on everything else, writes better docs, is a better general purpose agent and is overall more pleasant to use.
OpenAI@OpenAI

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one frontier model.

English
272
162
3.8K
410.5K
harsh
harsh@HarshOnInternet·
@Austen wish it was a 11 or 12" version
English
0
0
0
657
Austen Allred
Austen Allred@Austen·
“Only 8GB unified RAM on the $599 MacBook? Nowhere near enough to run a cluster of AI models…” That MacBook is for writing term papers on Google Docs and watching Netflix which is what 90% of computer usage actually is
English
270
1.1K
32.8K
517.3K
harsh
harsh@HarshOnInternet·
the new AWS is down so gotta go touch grass
harsh tweet media
English
0
0
0
319
harsh
harsh@HarshOnInternet·
@0xcuriousapple what's this a subtweet to lol what r u building
English
0
0
1
37
curiousapple
curiousapple@0xcuriousapple·
speed i m speed
English
2
0
2
282

Keşfet

@levelsio @nateliason @rachelgoodlad @mert @FurqanR @xai @cathrynlavery @Shaun__Furman