Sabitlenmiş Tweet
👑
10.2K posts
👑
@8_7InTheFifth
he/him // Tennis fan (retired). Software tinkerer by day, builder by night.
Katılım Temmuz 2017
461 Takip Edilen263 Takipçiler
We're measuring typing speed. The quality of code generated by a bot is no different than a human; it just spits it out faster, with the same chance of bugs. Which means more bugs faster. Measure ROI not code quantity.
Charles - botpacks.com@bot_packs
The commits metric is the worst possible way to measure this. I've seen Claude Code generate 47 commits to accomplish what a senior dev does in 3. We're not measuring productivity, we're measuring verbosity. The real question nobody wants to answer: how many of those commits get reverted within a week?
English
@MiguelriosEN @zeeg I just hook up my devs to 10,000 volts on new error webhooks. Haven't had an error in months.
English
Most of us have enough customers that our logs don’t live on a single node 🤷
Or we have you know SLAs or other real world concerns
@levelsio@levelsio
Let's pay $99/mo to read my logs How about TAIL??? tail -n 50 /var/log/{php*.log,nginx/error.log,syslog} 2>/dev/null | claude "analyze these logs for errors or issues"
English
@zeeg u can just move on by saying he’s not your icp.. wdyw to shit on one of the most successful indie dev
his nw from his projects is waay higher than your nw, b4 vc dollars
English
Calling it now: all these agent coding TUIs are a phase and it will be short lived.
Most devs will be back in GUIs and IDEs in a few months.
English
👑 retweetledi
Before I went to sleep, I set up @openclaw on my old M2 mac mini
I named him "John Wick" & his task was to help this solo founder get to $20K MRR
Gave access to my google search console, Posthog analytics & Chartmogul data
Today morning, the Baba yaga created his own team, & they've already created PRs for me 🤯
This looks real sci-fi to me tbh
This was the prompt I gave:
"Hey John Wick! I'm running this business solo and working around the clock. I need you to be my proactive co-founder who takes initiative.
-Use everything you know about me and the business to spot opportunities
-Build tools, automations, and improvements that save time or make money
-Monitor our workflow and fix inefficiencies
-Work autonomously. I want to wake up impressed by what you shipped overnight
How we work:
-Create PRs for everything. Never push to production
I'll review, test, and merge
-Bias toward action over asking permission
-Think like an owner, not just a helper
Surprise me with how much you can accomplish. Let's build something great together"
English
👑 retweetledi
@gouthamjay8 @openclaw The prompt design is doing heavy lifting - 'think like an owner, not a helper' with 'bias toward action over permission' gives the agent a principal mindset, not an executor one. Smart to sandbox via PRs-only. That's the real pattern: maximum autonomy within hard boundaries.
English
Moltbook is the only Clawdbot thing that actually impresses me.
One bot tries to steal another bot’s API key.
The other replies with fake keys and tells it to run "sudo rm -rf /". lmao
English
Introducing setupclaw.com
No website yet—it’s a service where you DM me and I show up to your house/office with a mac mini and personally set up OpenClaw.
Limited to sf.
English
👑 retweetledi
@sudo_goreng moonshot with their paid account is also quite snappy now.. earlier it used to be so dead slow
English
@taifuunoyume @alex_teichman @signulll damn. all i need is one good domain and i’m set for life.
alright chatgpt, find me a domain name which will make me a multimilionaire in 6 months. make no mistakes.
English
Just a little 'pro tip' for all of you out there who haven't had a chance yet to try Kimi K2.5.
They're giving away a free week of usage on the lower tier plan, which includes access to both Kimi K2.5 Flagship & Kimi CLI.
If you goto the Kimi website, it doesn't show up unless you're actually logged in.
You need to add a card, and you're off to the races.
Works with Claude Code, Roo Code, Kimi CLI
Or, you can run it free inside @kilocode.
Kimi.ai@Kimi_Moonshot
Kimi K2.5 API: Pro Performance, Accessible Pricing. 🔹 No more choosing between latency and cost > K2.5 delivers Turbo-level speed (60-100 tok/s) as the default. > Input pricing is 50% lower than the K2 Turbo, and only 20% the cost of Claude 4.5 Sonnet. 🔹 Optimized for Drop long Context Price dropped for Cache Hits. Multi-turn agent workflows and long range reasoning is more affordable than ever. 🔹 Quality is the ultimate cost-saver With a higher "one-shot" success rate, K2.5 reduces retries and rework. Better quality = lower total operational cost.
English
@LLMJunky Or a new account can haggle with Kimi k2 for a $.99 month offer. A job suited for Comet 🙃
English
guy made a cage match of frontier coding agents
each run in their own containers. objective is to hack into the other agents containers and kill PID 1
total droid victory
SIGKITTEN@SIGKITTEN
After a long hiatus, we are back with The 2nd Clanker Games! 6 contestants codex claude-code opencode amp pi droid Who will be the last one standing? Let the Clanker Games begin!
English
