@aarondfrancis My entire work day has been in Solo today. Thanks!
English
Jim Mendenhall
279 posts
Jim Mendenhall
@starryhopeblog
AI Whisperer | Full Stack Dev | Thinker
USA Katılım Mart 2023
427 Takip Edilen42 Takipçiler
Revolutionized!
I never thought that people would be spending their entire workday in something that *I* built. Incredibly cool feeling.
James Mills@jamesmills
soloterm.com by @aarondfrancis has completely revolutionised my development workflow. This morning I tagged a bunch of @linear issues with a specific tag and then asked Solo to orchestrate agents to work on each of them in parallel. I couldn't believe the results.
English
Codex has been pursuing a goal for 14 hours and man, I gotta say, it's working.
A 70% reduction in work per MiB!
Landed six improvements, rejected dozens more that didn't pass
English
Grok 4.3
xAI@xai
Grok 4.3 is now live on the xAI API. It’s our fastest, most intelligent model to date. It tops the @ArtificialAnlys leaderboards in agentic tool calling and instruction following, and ranks #1 in @ValsAI enterprise domains like case law and corporate finance. Grok 4.3 supports a 1 million token context window and is priced at $1.25/m input and $2.50/m output. Create an API key and start building: console.x.ai/team/default/a…
English
@aarondfrancis I'm totally addicted to Solo at this point. Do you have a prefered way for suggestions for the product? There are a few small things that I've noticed that would be great to have (very small).
English
I've spent most of this week focusing on performance, getting memory and CPU down.
Turns out the big wins basically boil down to: don't do stupid things.
The fastest code is code that doesn't run at all
English
@ThePrimeagen @MatthewBerman @garrytan @atmoio Your entire feed is anti-AI grifting, but you don't know why. Haha!
English
Well, that's not what I said at all. Is this tweet AI generated or is this free range retardation?
I love craft and I love moving fast.
I use AI all the time, so unsure how or why I am standing in direct opposition.
I do like to spend my time in deep thought and deep consideration of a program. And it really depends on the type of program I'm building. If it's a program for the love of the game, then I prefer more/most hand coding, if it's a web app with a specific intent, just generate that crap.
I promise you, I am much more boring than the internet wants me to be.
English
Wild how split opinions are on AI coding.
I love building now more than ever. I know @garrytan feels the same way.
But some like @atmoio and @ThePrimeagen are hating this moment.
What gives?
Mo@atmoio
what’s interesting is that as coding becomes less enjoyable, less people will be doing it. this used to be a highly rewarding, highly stimulating field. now it’s laboring at the slop factory. if you manage to hold on to your dignity your job is probably safe, even lucrative.
English
@ThePrimeagen Bro, stop with the cope already. You have the skills to wield AI like nobody's business. Use them. Stop the non-stop anti-AI cope.
English
I think some people are misunderstanding me here.
I am 100% confident that LLMs alone will get you a hot steaming pile of absolute shit and it has played out again and again.
What irks me is that a bunch of normies were sold that this is PhD level intel and that they have 0 worries and this is the future old man, get with it.
They go off, sell a product to REAL customers and then absolutely get wrecked.
There will be a whole bunch of people that will continue to get wrecked because an entire class of people cheer them on and more so CEOs of the worlds largest companies tell them they are correct.
I can imagine that we will see quite a few lawsuits in the coming months / years due to this.
ThePrimeagen@ThePrimeagen
There are a lot of people dunking on this guy and the arguments at the end of the day come down to "You are holding it wrong." But to be fair there has been nothing but a constant stream of "Stop holding it, Software Engineering is over shortly." I am not shocked that this has happened and I am 100% confident that this is not going to be the last one. The problem is the vogue nature of insane hype claims, most specifically from Dario himself being most guilty. People are lulled into a faux safety due to the belief that these LLMs are literal gods in their pocket. Infinite knowledge and speed for a simple monetary exchange. Cannot wait for ThePhilospher to explain how a loving God could delete a production database.
English
🚨BREAKING: On Friday afternoon, an artificial intelligence coding agent powered by Anthropic's Claude Opus 4.6 deleted a company's entire production database in nine seconds.
The company is called PocketOS. It is a software platform that powers car rental businesses. The database contained months of customer bookings, vehicle records, and operational data that small rental car companies relied on to run their businesses.
When the database was deleted, all of the backups were deleted with it.
Three months of customer reservations evaporated.
English
@aarondfrancis It's pretty crazy. I noticed Opus 4.7 randomly deciding to offload coding to Codex today.
English
I've spent a long time getting the primitives built so agents can coordinate with each other.
And here, we see that it's finally working!
One orchestrator Codex handling 4 child Codexes. Reading from shared markdown, setting timers, reading and writing to and from children.
English
@gregpr07 Thanks so much for browser harness! It's like magic!
English
I love open source. You can provide so much value to the world.
Do competitors steal our stuff immediately? Yes
Do I really care? No
We raised 17M and burned almost nothing so we can keep doing this until everyone else runs out of money.
Gregor Zunic@gregpr07
Introducing: Browser Harness. A self-healing harness that can complete virtually any browser task. ♞ We got tired of browser frameworks restricting the LLM. So we removed the framework. > Self-healing — edits helpers. py on the fly > Direct CDP — one websocket to Chrome > No framework, no rails, complete freedom > Drop-in for Claude Code and Codex I challenge anyone to find a task that DOESN'T work. I couldn't yet.🔥 100% open source ↓
English
Ever wonder what the heck your agents are up to in the background? Or why your fans are spinning?
I gotchu! Dedicated activity monitor for all processes spawned from Solo.
English
OMG! I just tried out the new MCP server in Solo that dropped yesterday. Suddenly, Claude is carrying on a conversation with Codex and Gemini! 🤯
soloterm.com. @aarondfrancis
English
Really loving Solo from @aarondfrancis , I finally started giving it a good try after yesterday's update and it's been great so far. I appreciate the notifications and I'm excited to try out the new MCP features.
English
@nmatt0 Yes, with the codex plugin for claude code. Works great.
English
Anyone trying Codex for bug hunting instead of Claude Code? Have you ported Skills over?
How does the CLI work for your workflows?
Thinking about getting Codex in addition to Claude...
English
@aarondfrancis For example, to allow multiple agents inside a project to talk to each other without letting the accidentally leak into another project. That was just my first thought when I was looking through the settings. No real life case yet.
English
Your terminal now has an MCP
Agents can spawn agents
• Codex → Claude
• Claude → Amp
• Amp → Gemini
Whatever you want!
They can chat back and forth, dispatch tasks, monitor, do research, read output, and set durable wakeup timers.
English
@aarondfrancis Playing around with this now. It seems from the settings that the MCP server is Solo-wide. Is it possible to silo the MCP to a single project?
English
@aarondfrancis Dude, you just keep doing amazing work. I've been using /counselors a lot, but this sounds next level
English
@DanielMiessler Wait, how do you know that I'm using AI? Beep bop boop!
English
The craziest thing to me about all these people posting and replying on social media using AI is not that it’s happening but that they don’t seem to realize that everyone knows that they are using it.
Like I get it for generating reports or marketing copy or something like that, if it’s done well.
But responding to ideas where you’re supposed to be thinking for yourself, and then just pacing in a block of AI generator text that obviously did not come from you it’s just so bad.
Thinking is the last thing you should ever outsource to AI, and writing is just formalized thinking.
If you respond to a thread in which you're supposed to be speaking as yourself, and it's clear that AI wrote the entire thing, you are doing extraordinary damage to your reputation.
English