Dax Raad
Builds developer tools — SST, and now OpenCode at Anomaly. Posts constantly on x.com and writes almost never; the blog stopped in 2021.
Dax Raad did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest x.com
What they believe
-
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
every week i see a new benchmark that ranks claude code last and everyone pats themselves on the back for not using claude code and being "smarter" and it's still #1 and still growing faster than most of the other things on the list this has been going on for a year
x.comSaid 3 Sept 2026This on korrents
-
When a benchmark disagrees with what people actually adopt, what it is telling you is that the thing it measures does not matter.
what the benchmark is actually telling you is the shit you think matters does not matter
x.comSaid 3 Sept 2026This on korrents
The bold line is korrents’ wording; the quote is theirs. These 2: what they wrote before what they said aloud, one per source, newest first.
Feed
As its own page →Hiding
14 October
13 October
12 October
29 September
-
Recommendsrcmnd.app
opencode miniTheir words
probably a good time to mention `opencode mini` which is a minimal scrollback version of opencode
24 September
-
Recommendsrcmnd.app
OpenCode DesktopTheir words
there's 2M weekly active users using OpenCode Desktop it's now about at 50% of TUI users it's a great time to try it
3 September
-
korrents.com
A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on.Their words
people ask us if we'll train our own model and the answer currently is no 1. we are too dumb to 2. there's plenty of other well funded efforts 3. we need to remain a neutral ground for models to battle
-
open sourceAnthropicOpenAIChina
Their words
in this whole USA vs China thing OpenAI and Anthropic aren't relevant because they're positioned differently them building better models doesn't hurt china at all the competitor has to be - american - open source - enough compute to do inference at scale that can shift things
-
Their words
what the benchmark is actually telling you is the shit you think matters does not matter
+ 1 more
-
Their words
every week i see a new benchmark that ranks claude code last and everyone pats themselves on the back for not using claude code and being "smarter" and it's still #1 and still growing faster than most of the other things on the list this has been going on for a year
-
Usesrcmnd.app
HoneycombTheir words
i analyzed a weeks worth of data via honeycomb + planetscale mcp and opencode2's codemode
-
Usesrcmnd.app
PlanetScaleTheir words
i analyzed a weeks worth of data via honeycomb + planetscale mcp and opencode2's codemode
-
Usestheir ownrcmnd.app
OpenCodeTheir words
then setup a script to email 140,000 impacted users with personalized instructions for how to fix the tool they're using all on OpenCode's muse spark free tier
+ 1 more
-
Likedtheir ownrcmnd.app
muse sparkTheir words
muse spark 1.3 reminding me how much i missed fast models
2 July
27 May
From one piece Building OpenCode with Dax Raad 11 beliefs · youtube.com
-
Their words
There's always negative sentiment that exists for any business that's getting hyped. They have no incentive to correct it. Um so again it's complicated because I know the training costs are a big part of it. Uh the R&D department is is hugely expensive but long-term inference makes sense as a business and I think it it always will.
-
Their words
cuz because we rent GPUs at scale to run the models and we still use middleman by the way. So we're not like going all the way down to the down to the floor. Even for us there are some models the sticker price and the cost to us there's like an 80% margin in there.
-
Their words
And our harness wasn't very good for like the first like five months of open code. But it was good enough. It was good enough that most people couldn't really tell a difference. And once we won enough share, then we went back and like tried to make our harness like good and smart and optimize and all those things. But uh it was inverted from what everybody else was doing. Everybody else was being like you have to build the smartest harness and that's how you win.
+ 8 more
-
Their words
The the biggest advantage to in DevTools is the fact that everyone working at DevTools is a programmer and programmers are horrible at B2C products. They don't realize DevTools are B2C products.
-
Their words
every single dev tool we use whether it's databases, compilers, whatever eventually the open source option becomes a default option, right?
-
Their words
If you get your positioning right, the world just keeps handing you wins that you didn't even expect. So like we never predicted this exact scenario but like our fundamental understanding of the position was right. like if if there is a neutral party, all these companies with billions of dollars will kind of use a neutral party to advance their own like company's interests.
-
Their words
the strategy that we know how to play really well is to pick one temporary bad guy and then galvanize all their competitors to push something forward against them.
-
Their words
none of our competitors are crushing us either. Like no one out there is using AI so well that they just like we can't even compete, right? Um, and we're in the coding agent space. All our competitors are super into AI. So you would think in our space there would be like uh a huge gap, but there there just isn't.
-
Their words
The moment you ship something, you're stuck supporting it forever. And by supporting, it means any future feature you build is going to like interact with it. So you still have to be very conservative with what you put out there. It's hard to undo anything. Just cuz we can ship 10 times more doesn't mean we have 10 times as many good ideas to ship out there.
-
Their words
If you add that up, you think, "Oh, we shipped a thousand features. Now that adds it to a good product." It actually adds it to a horrible product.
-
Their words
But I've always thought it's better to think a lot instead of swinging a lot. I think you could you can eliminate a lot of ideas or directions just by, you know, spending a lot of time in your head and with your team talking. Um, obviously AI doesn't speed that part up.
5 December 2025
22 September 2023
Nothing matches.
Beliefs
Korrents What they believe 28 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
every week i see a new benchmark that ranks claude code last and everyone pats themselves on the back for not using claude code and being "smarter" and it's still #1 and still growing faster than most of the other things on the list this has been going on for a year
@thdxr on X Said 3 Sept 2026
When a benchmark disagrees with what people actually adopt, what it is telling you is that the thing it measures does not matter.
what the benchmark is actually telling you is the shit you think matters does not matter
@thdxr on X Said 3 Sept 2026
In US-China AI competition the closed labs are beside the point; the competitor that shifts things must be American, open source and able to serve inference at scale.
in this whole USA vs China thing OpenAI and Anthropic aren't relevant because they're positioned differently them building better models doesn't hurt china at all the competitor has to be - american - open source - enough compute to do inference at scale that can shift things
@thdxr on X Said 3 Sept 2026
Show 25 more
A coding-agent company should not train its own model: it has to stay neutral ground for models to compete on.
people ask us if we'll train our own model and the answer currently is no 1. we are too dumb to 2. there's plenty of other well funded efforts 3. we need to remain a neutral ground for models to battle
@thdxr on X Said 3 Sept 2026
Before product-market fit, coding faster does not help: it is better to think a lot than to swing a lot, and AI does not speed up the thinking.
But I've always thought it's better to think a lot instead of swinging a lot. I think you could you can eliminate a lot of ideas or directions just by, you know, spending a lot of time in your head and with your team talking. Um, obviously AI doesn't speed that part up.
Building OpenCode with Dax Raad Said 27 May 2026
Answering every problem, competitor and user request with one more shipped feature does not add up to a good product; it adds up to a horrible one.
If you add that up, you think, "Oh, we shipped a thousand features. Now that adds it to a good product." It actually adds it to a horrible product.
Building OpenCode with Dax Raad Said 27 May 2026
Shipping ten times as much is not an advantage, because the moment you ship something you are stuck supporting it forever and every later feature has to interact with it.
The moment you ship something, you're stuck supporting it forever. And by supporting, it means any future feature you build is going to like interact with it. So you still have to be very conservative with what you put out there. It's hard to undo anything. Just cuz we can ship 10 times more doesn't mean we have 10 times as many good ideas to ship out there.
Building OpenCode with Dax Raad Said 27 May 2026
Nobody in the coding-agent market is using AI so much better than everyone else that their competitors cannot keep up — the gap you would expect to see simply is not there.
none of our competitors are crushing us either. Like no one out there is using AI so well that they just like we can't even compete, right? Um, and we're in the coding agent space. All our competitors are super into AI. So you would think in our space there would be like uh a huge gap, but there there just isn't.
Building OpenCode with Dax Raad Said 27 May 2026
A small company's most reliable play is to pick one temporary bad guy and galvanise all of their competitors into pushing something forward against them.
the strategy that we know how to play really well is to pick one temporary bad guy and then galvanize all their competitors to push something forward against them.
Building OpenCode with Dax Raad Said 27 May 2026
Get the positioning right and the world keeps handing you wins you never predicted, because well-funded rivals will all use a neutral party to advance their own interests.
If you get your positioning right, the world just keeps handing you wins that you didn't even expect. So like we never predicted this exact scenario but like our fundamental understanding of the position was right. like if if there is a neutral party, all these companies with billions of dollars will kind of use a neutral party to advance their own like company's interests.
Building OpenCode with Dax Raad Said 27 May 2026
In every developer-tool category — databases, compilers, whatever — the open source option eventually becomes the default option.
every single dev tool we use whether it's databases, compilers, whatever eventually the open source option becomes a default option, right?
Building OpenCode with Dax Raad Said 27 May 2026
Developer tools are consumer products, and the reason there are gaps to win is that programmers are horrible at consumer products and do not know it.
The the biggest advantage to in DevTools is the fact that everyone working at DevTools is a programmer and programmers are horrible at B2C products. They don't realize DevTools are B2C products.
Building OpenCode with Dax Raad Said 27 May 2026
The winning move in coding agents was inverted: take share with a merely good-enough harness first, then go back and make the harness smart.
And our harness wasn't very good for like the first like five months of open code. But it was good enough. It was good enough that most people couldn't really tell a difference. And once we won enough share, then we went back and like tried to make our harness like good and smart and optimize and all those things. But uh it was inverted from what everybody else was doing. Everybody else was being like you have to build the smartest harness and that's how you win.
Building OpenCode with Dax Raad Said 27 May 2026
Inference is a high-margin business even for a middleman: renting GPUs at scale, some models carry an eighty per cent margin over their sticker price.
cuz because we rent GPUs at scale to run the models and we still use middleman by the way. So we're not like going all the way down to the down to the floor. Even for us there are some models the sticker price and the cost to us there's like an 80% margin in there.
Building OpenCode with Dax Raad Said 27 May 2026
Every hyped business attracts negative sentiment nobody has an incentive to correct — and inference makes sense as a business long-term, whatever the training costs are.
There's always negative sentiment that exists for any business that's getting hyped. They have no incentive to correct it. Um so again it's complicated because I know the training costs are a big part of it. Uh the R&D department is is hugely expensive but long-term inference makes sense as a business and I think it it always will.
Building OpenCode with Dax Raad Said 27 May 2026
Demand for inference may be growing exponentially while GPU production can only grow linearly, and the tightening happens where those two lines cross.
The demand for inference is growing. So, like I don't think it's linearly growing. I think it might even be exponentially growing. But we haven't made our production of GPUs grow exponentially. That's like kind of a linear process. So as those lines intersect, there's going to be uh tightening.
Building OpenCode with Dax Raad Said 27 May 2026
Give an ordinary employee a button that does their work faster and they will do the same amount of work and keep the time — which makes complete sense.
You give them a button that lets them do their work faster. The natural place for them to do is hit that button as much as possible, do the same amount of work, and just cash in that extra time, right? Which makes total sense.
Building OpenCode with Dax Raad Said 27 May 2026
There is a world where AI coding tools change nothing except that engineers are happier, and for a lot of companies that is not good enough to keep paying for.
there is a world where the net result of all these AI coding tools is the same amount of work gets done, but all the engineers are happier because their job is easier. That's not good enough for a lot of companies. So, they're just going to say go back to typing out the code.
Building OpenCode with Dax Raad Said 27 May 2026
AI moved him from spending 95 per cent of his energy on deciding what to do to spending 96 per cent — a 20 per cent improvement that feels like no change at all.
the joke I made was pre AI, I would spend 95% of my energy thinking about what to do and 5% of my energy doing it. Now I spend 96% of my time thinking about what to do and 4% of my time actually doing it. So yeah, it's like a 20% improvement, but dayto-day it feels as hard as ever.
Building OpenCode with Dax Raad Said 27 May 2026
The judgement call about whether to absorb a hack is distorted right now, because the agent will simply do the hacky thing and deal with the consequences for you.
That judgment, that ability to have that judgment is so distorted right now because the agent will just do the hacky thing for you. The agent will kind of deal with the hacky problems that come down the road. And it's way easier just to be like, "Oh yeah, it's a temporary fix."
Building OpenCode with Dax Raad Said 27 May 2026
The prickle you used to feel writing a hack is muted now, so the landmines are still there but the feedback loop that kept your judgement honest is gone.
That prickle that feeling that you get, it's like muted now cuz someone else it's kind of like you've made someone else deal with the problem. The problem is still there and the the landmines are still going to blow up on you eventually, but like you're not you don't feel that bad feeling as much anymore. So your judgment is skewed. You're not getting that feedback loop.
Building OpenCode with Dax Raad Said 27 May 2026
Almost every confident prediction about AI is a defence mechanism: people asserting a future in which they personally turn out to be the winner.
It's like everyone is just saying mantras to themselves cuz the root thing that's going on here is we are experiencing a moment of great change. Everyone is very nervous about what that means for their own position in it. a defense mechanism is to confidently assert a future in which you're a winner. And that's almost what every single prediction that you see is happening.
Building OpenCode with Dax Raad Said 27 May 2026
You probably only have one good idea in your whole product, and the job is getting the user to experience it as fast as possible.
You probably only have one good idea in your whole product. Get the user to experience that as fast as possible. Well, it sounds so easy, but if you go try every single product out there, you will see a million accidental steps they introduced from the user hearing about your product to like seeing the value in it.
Building OpenCode with Dax Raad Said 27 May 2026
The job of product is not to ship the immediate solution to a problem but to absorb all the problems and find the one solution that fixes fifty of them.
The job of product isn't to just receive a problem and ship the immediate solution. It's to absorb all the problems and understand that there's one solution you can ship to fix 50 different problems.
Building OpenCode with Dax Raad Said 27 May 2026
Quality comes from doing irrational things — half of what you do you did not have to do — and almost nobody is willing to operate that way.
I still believe quality is a huge differentiator. It's not just something you can decide to do. I think it needs to show up every single aspect of your company from like you have to do things that are irrational. I think that's kind of what quality comes from. like you do a bunch of things and like 50% of those things you you didn't have to do and I think very few people are willing to operate that way.
Building OpenCode with Dax Raad Said 27 May 2026
Redefining the engineer's job as building guardrails is not novel — it is the same problem as making a junior engineer effective, which we never solved either.
The thing that I find interesting is that's not novel. This has been the thing we've always been trying to do forever. How do we get a junior engineer to ship code safely without breaking stuff? Right? How do we make patterns in the codebase? How do we make tests? Like it's it's all the old stuff that we've always wanted to do.
Building OpenCode with Dax Raad Said 27 May 2026
The verbose enterprise patterns everyone hated are worth having again: coding agents are idiots working around the clock, and you are not the one typing the boilerplate any more.
We're now doing it in a much heavier way because we find that these like kind of bory enterprisey uh patterns end up being pretty useful because you have a bunch of idiots on your team now. The coding agents are a bunch of idiots and they are going to work 24/7 and they're going to like ship a lot of stuff. So you need way more guardrails than you used to.
Building OpenCode with Dax Raad Said 27 May 2026
Being a decent software engineer plus a genuine expert in one industry is a deadly combination, and engineers are the only people who get to change industries at will.
But you if you also become an expert in a specific industry, that's like a deadly combo. Um if you are like just pick any industry, let's say let's say farming, let's say you understand that farming industry really well and you're also a decent software engineer, you're probably like the top 10 people in the world for that combination that the whole industry will want to hire.
Building OpenCode with Dax Raad Said 27 May 2026
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Recommends rcmnd
rcmnd What they recommend 9 things, 10 mentions — each backed by an exact quote.
Compiled by rcmnd.app, not by them: the quotes are theirs, and each links to the post it was copied from.
Recent
Recommends opencode mini
probably a good time to mention `opencode mini` which is a minimal scrollback version of opencode
x.com 29 Sept 2026
Recommends OpenCode Desktop
there's 2M weekly active users using OpenCode Desktop it's now about at 50% of TUI users it's a great time to try it
x.com 24 Sept 2026
Liked muse spark
Show 7 more
Uses OpenCode
then setup a script to email 140,000 impacted users with personalized instructions for how to fix the tool they're using all on OpenCode's muse spark free tier
x.com 3 Sept 2026
their own
Uses PlanetScale
i analyzed a weeks worth of data via honeycomb + planetscale mcp and opencode2's codemode
x.com 3 Sept 2026
Uses Honeycomb
i analyzed a weeks worth of data via honeycomb + planetscale mcp and opencode2's codemode
x.com 3 Sept 2026
Loved Kysely
To connect to these various databases I am using the incredible library by Sami Koskimäki called Kysely
thdxr.com 20 Oct 2021
Recommends PlanetScale
That said, I'd personally pick Planetscale in this situation.
thdxr.com 20 Oct 2021
Recommends Fauna
I typically recommend looking at serverless native databases like DynamoDB or Fauna however they do not work for all preferences or workloads.
thdxr.com 20 Oct 2021
Recommends DynamoDB
I typically recommend looking at serverless native databases like DynamoDB or Fauna however they do not work for all preferences or workloads.
thdxr.com 20 Oct 2021
Where they publish
Site thdxr.com A blog he stopped writing in 2021; kept because it is the link he still gives out.
Three posts on AWS Lambda and databases, the newest from October 2021. It is listed because it is the site his own accounts point at, not because anything new lands here — his own line on it is "I build things then try to remember to write about them."
Link verified 3 Sept 2026.
x.com @thdxr The main channel by far: OpenCode, agents, and what he thinks of the discourse.
High volume and where nearly everything lands first — building OpenCode in the open, arguments about coding agents and benchmarks, and running commentary on the AI industry. The blog has been quiet for years; this has not.
Recent
- what are you guys doing you're so embarrassing 14 Oct 2026
- testing out a new game concept, help 14 Oct 2026 anoma.ly
- a good portion of the best engineers have moved around to companies where they can more directly work with ai so you see founders of the companies they're leaving posting how they're doing really interesting ai work but it's futile, competing for talent is impossible right now 14 Oct 2026
Show 17 more
- everyone reads this and is like "he's talking about me" sorry man, probably not 14 Oct 2026
- it's crazy how easy it is to spot 10x engineers these days for a certain set of people LLMs totally unlocked their potential to the point where imagining their life before this seems totally depressing 13 Oct 2026
- google has finally done it this is very much a frontier model it was the second highest used model last week by our team they're in the race now 13 Oct 2026
- we're getting better at this 13 Oct 2026
- this is the future of coding agents 13 Oct 2026
- going from image gen of many angles of a 3D model to the actual 3D model needs to be solved right now i can get close and sometimes get lucky with enough tokens but if this gets made easy man its gonna be so good 13 Oct 2026
- opentunnel is my first ever multi region deployment (ignoring cf or cdn stuff) pretty cool 12 Oct 2026
- we started this project over a year ago because opencode needed an authoritative list of models it now powers so many other products we're working on a v2 api shape now to better represent a few things 12 Oct 2026
- staying relevant is the hardest thing in the world look at all the devtool companies that had mindshare even just a few years ago completely lost all relevance with this new shift 12 Oct 2026
- we're about to go on a run 12 Oct 2026
- David Hill has reportedly joined OnlyFans 12 Oct 2026
- the worst part about ghost writers on here is founders do it on their personal accounts so they're hiring people to make it seem like they're funny so pathetic 12 Oct 2026
- our team is fully addicted to the opencode mobile app, kind of unexpected testflight link is pinned to my profile and we're trying to get through apple verification now and will kick off android soon 12 Oct 2026
- opus 5.5 has had a crazy impact on our team you can probably even observe it externally with everything we're putting out 12 Oct 2026
- yes just your standard blog post complete with wet matter synthetic organ data transfer 12 Oct 2026
- the reason you see so many predictions is most founders haven't reached product market fit they're hoping the next thing they're working on is what blows them up, hence "the future of x will be <thing we're working on>" but most of the time it's just an incremental feature 12 Oct 2026
- guys we did it we finished another blog post. see it's a regular blog post. just text and words and such placed in the right order. no distractions. we focused on the words. yes 12 Oct 2026
Link verified 3 Sept 2026. Recent items update automatically from the channel.
GitHub thdxr SST, OpenCode, and the tools underneath them.
The work itself. For someone who writes almost nothing, the repositories and the pull requests are the record of what was actually built.
Recent
- environment 2 Jul 2026
- docs 5 Dec 2025
- ampt-api — Ampt app for ampt-api 22 Sept 2023
Link verified 3 Sept 2026. Recent items update automatically from the channel.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.