Entrepreneur / Engineer / AI Enthusiast / Aspiring Triathlete. I build with Ruby, craft intelligent systems, and lead with heart. Let’s enjoy the thrill.
Las Vegas, Nevada
Joined May 2008
- Tweets5.4K
- Following168
- Followers1.4K
- Likes4.4K
Chris Hough 🎰 retweeted
THIS IS AN ACTUAL F*CKING GOLDMINE
Anthropic just shared one of the best tricks for Claude Code.
The idea: run Sonnet, Haiku 5.5 and Opus 5.5 at once, each one doing only the job it's best at.
Better results and way fewer tokens, because every task lands on the right model.
You just launch Claude Code like this:
claude --model sonnet --advisor opus
here's the split:
→ Sonnet 5.5 runs the session, writes the code and applies the fixes
→ Haiku 5.5 swarms the repo in parallel: search, grep and diff audits
→ Opus 5.5 stays on call as advisor for the big calls and signs off on the diff
→ you stop burning Opus context on work that doesn't need it
Opus only steps in at three moments:
→ before a plan locks
→ when the same error shows up twice
→ before calling it done
Sonnet builds. Haiku swarms. Opus reviews.
JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split
the full tree
> Sonnet 5.5 runs the main session and coordinates the work
> search maps the repo on Haiku 5.5, read-only
> grep finds call sites on Haiku 5.5 in its own context
> audit checks the diff on Haiku 5.5 in a throwaway worktree
> Opus 5.5 on call as advisor, reviews the synthesized diff before sign-off
> JEV routes micro-forks in milliseconds
paste the tree and this prompt into Claude Code ↓
"Reconfigure my Claude Code setup around this tree:
1. Run the main session on Sonnet 5.5 with Opus 5.5 as advisor.
2. Create three Haiku 5.5 subagents in .claude/agents: search (maps the repo), grep (finds call sites), audit (checks the diff).
3. Set isolation: worktree on audit so its checks never touch my working branch.
4. Add one rule to CLAUDE.md: delegate every repo search and test run to the Haiku 5.5 subagents to keep the main context small.
5. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. No edits until I say go."
↳ code.claude.com/docs/en/sub-…
save it, it'll come in handy.
Chris Hough 🎰 retweeted
This is f*cking insane. SpaceXAI Senior Engineer, Lauren Tan:
“GrokBot is the most powerful agentic tool we’ve ever shipped, but 99% of users use it wrong.
At SpaceXAI I’m running a team of 100+ GrokBot agents — Chief of Staff, 10 managers, and 90+ workers.
That’s the new engineering setup in 2026.”
In 40 minutes, she shows exactly how to get 100% out of every agentic tool you’re using.
GrokBot → Chief of Staff → Managers → 90+ Workers → Full Team
Worth more than any $5000 agentic course on the internet.
Skip Netflix and watch it today — it will change the way you use GrokBot forever.
Then read the GrokBot engineering guide below to build your own GrokBot team ↓
“If you are serious about growth, be serious about accountability. If you are serious about abundance, be serious about gratitude.! you are serious about intimacy, be serious about vulnerability. If you are serious about discipline, be serious about delayed gratification.”
〰️ Wise Person from the WWW!
📍OfKors Cafe ( @ofkorscafe )
Address: 1989 Main St, Sarasota, FL 34236
Folks always think my meals require the most complexity, when in reality I eat the same setup at home, nearly every day, fitness-focused, bland fuel. It’s a blessing to find such legendary simple items like this. During my travels to Sarasota, this spot was my favorite. This simple dish I pray to replicate at home filled my foodie cravings almost every morning.
🎰🌻💀⏳ 🙈🙉🙊
#foodietravels #dailyfeastinspiration
#hough2026 #rubyistfoodie #aienthusiast
#aspiringtriathlete #extremeownership
23
There's people you fall in love with, but can't build a life with. Then there's people you can build a life with, but you don't have the deepest chemistry with. Then there's Kingdom partners. Kingdom partners are both Growth-oriented and God-oriented beings. They are not ego partners, they are spiritual Evolutionary partners that you experience mental emotional physical and spiritual resonance with. You are brought together to conquer in both the material and spiritual world. You become one in both the terrestrial and celestial spheres. They are the ones that hold you in tender & sometimes tough love so you can ultimately enter the Kingdom of Heaven. These partnerships are eternal.
〰️ERYKA STANTON ( @empowered.by.eryka )
📍Hikiniku to Come ( @hikiniku.to.come )
Address: Kyoto, Japan
One of the best meals I have ever had, omg! I had 5 of these burgers and bought a shirt on my way out!
🎰🌻💀⏳ 🙈🙉🙊
#foodietravels #dailyfeastinspiration
#hough2026 #rubyistfoodie #aienthusiast
#aspiringtriathlete #extremeownership
23
Chris Hough 🎰 retweeted
Let me explain reality… if you have but sixty seconds:
They were targeting Elon
They were targeting him with fake charges because the socialist-industrial complex is terrified that he would expose their long grift.
They came after him for the Model 3 and Elon’s claims around its potential.
That potential was realized, and it became, along with the Model Y, the best-selling electric vehicle ever created.
These were fake charges to try to stop somebody from building the best category-defining product.
Let that sink in: that's how evil these motherfuckers are.
The loooooong grift has been exposed: socialist grifters are stealing our tax dollars to fund fringe lunacy, NGOs and government programs without oversight or audits.
They’re parasites incapable of creating any product or service that has to compete in the open market.
Elon creates a couple of cutting-edge products each year, and half of them succeed.
Some of them actually change the world. Some of them fail brutally.
It's called capitalism. It's called creation.
This is what moves the human condition forward: trying things.
Trying really hard things.
Socialists come for the people building valuable products and services — that’s the tell
Keep your eye out for the people who've created nothing and risked nothing, but who are attacking the people who risk everything to create Something.
That's the tell.
Chris Hough 🎰 retweeted
I get what she is saying. Historically, you have
- Human slop cannon
- People who think all code should be Good Code, who are very useful because of talent but requiring management because of the constant desire to boil the ocean / move at the speed of a snail
- People who think important (seams, data modeling, rules engines, stuff like that) code should be Good Code, and its fine if other code is slop
The most valuable persona is the third. The first will destroy a business due to overrunning tech debt, the second will tank a business due to neverending refinement. The third understands those forces need to be kept in balance.
I have a huge amount of respect for Lauren, I know folks who have worked with her and say she is absolute top tier. I know she spent a huge amount of time and effort working through Dune for example. There was probably a non trivial amount of code involved there, and it probably is the kind of thing that needed to be Good Code.
"Slop is a slur" I think is cope. "Most code in the before-times was slop and that was ok" I think is reasonable and defensible. "All code is slop" I think is an overreach, and dismisses a very important part of this conversation.
codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software.
swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go.
admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?".
well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is:
• correct
• bug free
• fast and cost efficient to run
it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start.
but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing!
agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale.
the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree
Chris Hough 🎰 retweeted
i feel like swe interviews could probably collapse into just 2 technical rounds:
• system design (how well can you articulate your ideas, do you actually know how to engineer something)
• onsite project to build a real thing with agents (can you translate your intent into high quality outcomes)
everything else we used to ask is no longer necessary
🗞️ if your team is too busy doing their 'normal job' to experiment with AI, you're preparing them to be replaced
ghuntley.com/replaced/
In this post, I guess this's the last time I'll say it. AI use is no longer optional if you wish to be employed. What follows is advice for current employees and hiring managers on how to hire in 2026 to source AI-first candidates.
The Rare Person Theory
Once in a while, you meet someone who changes the way the world feels.
Around them, you become happier, lighter, and brighter. You laugh like you did as a child. You speak without fear of being judged. You slow the hustle version of yourself. They make everything feel like an adventure. They turn ordinary days into movie scenes. They bend time without trying. These people are rare, if you find one, hold on tight, they don't come twice.
📍Tora Toriya / 炭火焼鶏と一口餃子 TORA鶏YA 四条河原町店.
Address: Kyoto, Japan
My first Japanese Yakitori experience with the Kyoto Ruby Meetup, it was legendary.
🎰🌻💀⏳ 🙈🙉🙊
#foodietravels #dailyfeastinspiration
#hough2026 #rubyistfoodie #aienthusiast
#aspiringtriathlete #extremeownership
2
55
Chris Hough 🎰 retweeted
You're not going to believe how nasty Delta is.
Delta CEO Ed Bastian got caught trashing Elon Musk at internal meetings to explain why they rejected Starlink. But don't buy the corporate moral high ground for a second.
Delta tested Starlink, but Elon refused to let them trap passengers behind ad-tracking portals to farm and sell user data. SpaceX wanted instant connection just like home, with zero data harvesting.
So what did Delta do? They signed with Amazon’s completely untested satellite network which won't even launch fleetwide until 2028. Strictly to monetize passenger information.
United flyers get 300 Mbps; Delta flyers get dial-up and a data harvest.
Chris Hough 🎰 retweeted
Andrew Ross Sorkin gushes over Trump's new America. gov website on live TV while Joe Kernen sits there stunned.
Sorkin is not a Trump fan, and he lets that be known. But the moment he said the word "credit," Kernen nearly fell out of his chair.
SORKIN: “I want to be clear. I am actually not critical of the president in this instance at all, because I actually think it was great to bring everybody together.”
“For 29,000 websites, the ability to get a passport, the ability to get your medicare. I mean, the it was like being at a product. It was like being at an Apple product announcement. And when they went through what they did and the president was there in the morning and walked through what they were doing, and Marco Rubio was there, Scott Bessent was there, the whole cabinet was there. It was one of those moments where you actually thought the government was working for you, really? And Gebbia deserves an extraordinary amount of praise for it.”
KERNEN: “Do you feel great? Are you have the warmest fuzziest feeling right now listening.”
SORKIN: “And by the way, the president deserves credit for that."
KERNEN: "Oh my God!"
SORKIN: "Credit for putting you in that role. And Jeb and his team putting it all together.”
KERNEN: “So now I'm getting hot flashes. Wow. So this is just amazing.”
CONTEXT (What happened): Trump launched America. gov, a single government site meant to replace 29,000 federal websites for things like passports and Medicare. It was built by Airbnb co-founder Joe Gebbia, and Sorkin was in the room for the demo.
Sorkin also credited the Trump accounts interface as "really easy to use" and "like using a real app."
Unless a person has endured really dark and difficult things in their life, they simply will not have the emotional sensitivity or spiritual depth to relate to you at the level of soul. They won't really experience you or this life with holy wonder. They have not been initiated into the abyss of ego death to rise back into the light understanding the significance of your presence in their life. Find people that will treat you as sacred and appreciate the value of your soul.
〰️ @lewishuckstep
📍 Chyna Club ( @chynaclublasvegas )
Address: Fontainebleau
I did hear the bear dessert used to be a different animal, and the casino made them change it. As a crazy cat person, if it had been a cat, I would not have gotten it.
🎰🌻💀⏳ 🙈🙉🙊
#foodietravels #dailyfeastinspiration
#hough2026 #rubyistfoodie #aienthusiast
#aspiringtriathlete #extremeownership
1
41
Chris Hough 🎰 retweeted
Elon spending $20M on a domain just to troll Sam Altman is peak Silicon Valley villain behavior💀
AHAHAHAHAHAHAHAHAHAHAHA NO WAY.
> OpenAI just announced Dots.
> SpaceXAI bought Dot.com
it redirects straight to the Grok Bot download page. based lmao.
Chris Hough 🎰 retweeted
Austin is becoming one of the most important job engines in the country.
It doesn’t yet have the scale of a NYC, DFW, or Houston, but the combo of growth rate plus absolute jobs added is next level.
Chris Hough 🎰 retweeted
I was surprised how bad it was just walking from the hotel to the Rails World venue. One strung-out guy wanted to fight me for some reason, another was swinging wildly and swearing profusely. Lots of zombie vibes too. Whatever Austin is doing, it's not working.
2017: Austin spent $35 million on homelessness. 2,036 homeless counted.
2025: $118 million. 3,238 homeless.
Spending more than tripled and homelessness went up 59%.
If you service the homeless lifestyle, you will get more of it.
The NGOs that run this system get paid by the problem of homelessness, so they have no reason to end it -- in fact, their only incentive is to make sure the problem grows.
Chris Hough 🎰 retweeted
Early takeaways from Austin Deep Tech Week:
1. Austin is a serious f*cking city.
SF is still the center of gravity.
LA has built an absolute monster around aerospace, defense and industrials.
But after spending a few days in Austin, I'm increasingly convinced this city has structural advantages that the coasts underestimate.
People I've met here seem to have one primary objective:
Build.
Heads down. Gas pedal pinned to the floor.
Noticeably less obsession with looking important and more obsession with actually making shit work.
Deep tech rewards exactly that mentality.
2. Texas being aggressively pro-business isn't some Twitter talking point. It's an actual competitive advantage.
Heard versions of this repeatedly from founders and investors this week.
Permitting. Regulation. Taxes. Energy. Land. Manufacturing. Expansion.
When you're building software, you can abstract yourself away from geography.
When you're building atoms, geography becomes part of your cap table.
Every additional month waiting on a facility, permit, power connection or expansion is effectively dilution.
Texas understand that speed matters.
3. The coastal migration isn't over.
SF and LA still have unbelievable technical talent density, particularly at the earliest stages.
But the requirements change when a deep tech company starts working.
Now you need 100,000 square feet.
Power.
Testing.
Manufacturing.
Suppliers.
Technicians.
Hundreds of employees.
Suddenly Texas starts looking a hell of a lot more attractive.
And founders here don't seem nearly as worried about convincing talent to follow them as outsiders assume.
4. The next chapter isn't companies moving to Texas. It's companies starting here.
Historically the playbook has often been:
Coast → prove technology → raise capital → expand into Texas.
I think that increasingly becomes:
Texas → Texas → Texas.
More technical founders will move here before starting the company.
More pre-seed and seed companies will originate here.
More headquarters will be planted here from Day 1.
And that's when the flywheel gets interesting:
Talent → startups → capital → exits → experienced operators → new startups.
Once that loop starts compounding, ecosystems become very difficult to stop.
5. Austin feels significantly less distracted.
There is obviously bullshit everywhere. Startups attract grift like flies to shit.
But there's noticeably less keeping-up-with-the-Joneses energy here.
Less worrying about who raised what round.
Less optimizing for appearances.
Less obsession with which VC follows you or which dinner you got invited to.
More:
Does the thing actually work?
That cultural difference matters more than people realize.
6. “But the capital is on the coasts” is becoming a lazy argument.
Have you ever heard of a f*cking airplane?
It's 2026.
If you're building a generational company in Austin and a great investor in SF wants into the round, they're getting on the plane.
Great companies don't travel to capital.
Capital travels to great companies.
Austin already has serious institutional capital on the ground alongside a growing ecosystem of smaller funds.
More capital will follow the companies.
It always does.
7. Austin increasingly looks built for where deep tech is going, not where venture has been.
Deep tech is becoming less about a handful of scientists sitting in a Bay Area lab and increasingly about deploying massive amounts of physical infrastructure.
Factories.
Energy.
Robotics.
Defense.
Space.
Advanced manufacturing.
Data centers.
Industrial systems.
Those businesses eventually collide with the physical world.
And the physical world cares about land, power, regulation, labor, logistics and speed.
Texas has a lot of all six.
SF still has the deepest venture ecosystem. LA has built an extraordinary deep tech machine.
But Austin doesn't need to become either of them.
It may be building something fundamentally different:
A startup ecosystem optimized not just for inventing hard technology — but for actually industrializing it.
That's a much more interesting proposition.
Came into Austin Deep Tech Week thinking this was an important emerging hard tech ecosystem.
Now thinking “emerging” might already be outdated.
Ingredients are here.
Talent is coming.
Capital will follow.
Unlike a lot of startup ecosystems I've visited, Austin feels like it actually wants you to build shit here.
That's a hell of a tailwind 🏭🇺🇸
Finally - mad props @Andercot, @CaitlinCloud9, @Jason_A_Scharf + many others for putting this together & making this a kickass week!