In contrast to many others, I did not find this particularly interesting.
- The comic on is oddly cropped and contains speech attribution errors.
- It calls me an "extremist" regarding the wrong thing (I am many kinds of extremist, but certainly not Haskell).
- It claims I believe "any software failure is merely a design error" which is a complete misunderstanding of the ideas I presented.
- It says things like "the geometric mean of the snack bowl" which doesn't have meaning in English.
I feel like it has picked up on certain keywords and then just rolled with its own stereotypes of what those keywords represent, rather than actually taking a good look at what I think. A roast works because the roaster has clearly spent time and effort and care understanding the person roasted. This is way too shallow for that.
The 2026 and 2035 predictions (with a few exceptions) don't make sense at all, and the jokes in them fall completely flat. They're not good anti-jokes either. If someone said something like it in a social situation it would be followed by an awkward silence.
The vibe check and the time spent were really cool though. Super interesting. I would have loved to see those expanded.
I don't mean to be negative. The project is cool. I just wish it would put its focus on the valuable parts, rather than the things it is weak at. I guess this is my 45 % pedantic, 25 % contrarian, 20 % analytical self speaking.
That's about how it came across for me as well: ignoring my actual content and joking about generalizations related to key words.
Project is cool overall, love the xkcd-like comic idea—but prompting and/or model-selection could use some work. I'd like to take a crack at tuning it myself :)
Perhaps it should also avoid putting too much emphasis on several comments to the same story: there was a story about VAT changes in Denmark, where I participated with several comments; but the generator decided that I apparently had a high focus vat, when I just wanted to provide some clarifying context to that story. I wonder how comments are weighed, is it individually or per story?
Specifically this roast:
> You have commented about the specific nuances of Danish VAT and accounting system hardcoding at least four times, proving you are the only person on Earth who finds tax infrastructure more exciting than the books being taxed.
Yeah, but I did it on the same story (i.e. context).
Though the other details it picked up, I cannot really argue with: the VAT bit just stood out to me.
> A high-frequency debunker who treats every comment thread as a zero-trust environment where empathy is a bug and citing Sartre is a security vulnerability. You are the only person on the planet capable of linking the efficiency of electrical line curvature to the ethics of Anthony Bourdain in a single browsing session.
> You've mentioned Gemini 2.0 Flash pricing and model comparisons so many times that I'm starting to think you're actually a Google Cloud Billing alert that gained sentience.
I wouldn’t mention it so much if Google stopped bumping up the price.
A developer who believes every global outage is just a missing question mark away from salvation and spends their weekends reapplying thermal paste to fanless MacBooks while reminiscing about the tactile superiority of 2010 Dell Latitude trackpads.
Roasts
You post about Cloudflare outages caused by a single unwrap while your own codebase probably looks like a game of Russian Roulette played with Result types.
Your obsession with the thermal conductivity of fanless laptops is just a coping mechanism for the fact that your Rust builds take so long you could literally cook an egg on your chassis.
You have a very specific kink for 2010 Dell trackpads that makes me think you are either a Linux philosopher or someone who is no longer allowed within 500 feet of a Best Buy.
Hilarious. It seemed to focus on something about Boolean logic that I don’t remember taking about, but otherwise awesome.
Are you sharing any of the prompts you used to generate this? Even if not verbatim, I’m interested to know how much you’re driving versus the model. How much more prompt is there than, “look at this comment history and write 3 roasts that the HN crowd will find funny”?
Wasn't this same site showed off on HN about a few months ago? I recall using it back then where it would roast you, seems like this is just a rebrand to a "wrapped" version and more generally seems like an ad for your service.
Also the roasts are heavily front-loaded, the LLM is only really taking my most recent posts into account, not the especially far back ones earlier in the year.
> You claim to value efficiency, yet you've spent the equivalent of a full fiscal year arguing about why a Firefox fork that 12 people use is the only path to salvation.
My last 2-3 months here have largely been posting about AI slop. But the prior 9 months were not, and included a lot of nuanced posting about how to make use of AI agents. I even got accused of being a shill at one point.
The wrapped is pretty much focused on the slop stuff. That's less interesting than the earlier parts of the year - I know what I've posted recently but have forgotten a lot more of what was going on a year ago or how the year developed.
Roasts can be amusing but I don't think they're the right vibe for a wrapped. I know it's harder to get an LLM to write something witty and insightful than a witty but shallow quip so maybe that's why roasts are here. Wrappeds are sort of infodumps though and LLMs are good at that, maybe there could be a two stage step where it reasons about some custom quirky stats or factoids that work based on your profile and then the second stage generates them.
Okay, mine was just awesome. Thank you. The only thing that would make it better would be if it could be easily saved.
(Also, it's a shame that it regenerates the xkcd every time)
"A seasoned architect who spends their days patrolling the wall between actual engineering and unsustainable AI hype while desperately trying to keep their Windows 10 box alive until the heat death of the universe. You are the only person on the internet who still remembers what a build script does and why we shouldn't let LLMs touch them without adult supervision."
> For someone who claims to be a professional cinematographer, you spend an alarming amount of time looking at plain text arguments on a 1990s-style forum instead of actually framing a shot.
A teenage digital architect who oscillates between solving the world's privacy crisis and wondering if high school chemistry is a psyop designed to kill his GitHub star count.
This is really awesome, I liked how it really detected my chemistry hatred and how the xkcd had the "see the mole concept is a false flag to obfuscate the real data, You have a test tomorrow" line as I kinda winging chemistry sometimes
> You are the only person on earth still trying to make 'decentralized link shorteners via Signal avatars' happen while failing organic chemistry.
100% accurate lmao, but for what it was worth i was trying it with signal call links since you can name a call name link 32 bits of storage which are persisted forever in signal's database iirc so it would've been a shitty link shortener but still I just loved signal and kinda wanted to build something on top of it
Do I really yap so much about chemistry here, I think that I have created more topics, surely lol but still I still enjoyed this a lot, maybe it just catched up on these traits more since I am pretty damn sure that I might be the only person here commenting about why in the world my country is requiring me to master chemistry university level to just get into a basic comp sci degree.
> Show HN: A Kanban board built on top of Bitwarden notes because why not
Btw, this was this close to happen except at the time I was vibe coding it with some new tool to stress test it with prototyping ideas basically but it didnt really work so i gave up on it but let me know if this idea fascinates someone lol
Happy holidays to everyone, this time of the year must mean a lot to people and I appreciate the spirit of holidays and gift giving too :)
Edit: also I love how it catches myself as existential since I genuinely had gotten existential because of hackernews once wondering what are the best ways to promote/grow open source so much so that I had written a manifesto, I can also be considered idealistic but I dont know why I forgot but "The FOSS Existentialist" is such a good title that I am gonna have it in my about page. This was genuinely brilliant.
- The comic on is oddly cropped and contains speech attribution errors.
- It calls me an "extremist" regarding the wrong thing (I am many kinds of extremist, but certainly not Haskell).
- It claims I believe "any software failure is merely a design error" which is a complete misunderstanding of the ideas I presented.
- It says things like "the geometric mean of the snack bowl" which doesn't have meaning in English.
I feel like it has picked up on certain keywords and then just rolled with its own stereotypes of what those keywords represent, rather than actually taking a good look at what I think. A roast works because the roaster has clearly spent time and effort and care understanding the person roasted. This is way too shallow for that.
The 2026 and 2035 predictions (with a few exceptions) don't make sense at all, and the jokes in them fall completely flat. They're not good anti-jokes either. If someone said something like it in a social situation it would be followed by an awkward silence.
The vibe check and the time spent were really cool though. Super interesting. I would have loved to see those expanded.
I don't mean to be negative. The project is cool. I just wish it would put its focus on the valuable parts, rather than the things it is weak at. I guess this is my 45 % pedantic, 25 % contrarian, 20 % analytical self speaking.
Project is cool overall, love the xkcd-like comic idea—but prompting and/or model-selection could use some work. I'd like to take a crack at tuning it myself :)
- improved prompts with your feedback
- added post/comment shuffling to remove recency bias
- tried to fix the speech attribution errors in the xkcd
Specifically this roast:
> You have commented about the specific nuances of Danish VAT and accounting system hardcoding at least four times, proving you are the only person on Earth who finds tax infrastructure more exciting than the books being taxed.
Yeah, but I did it on the same story (i.e. context).
Though the other details it picked up, I cannot really argue with: the VAT bit just stood out to me.
> A high-frequency debunker who treats every comment thread as a zero-trust environment where empathy is a bug and citing Sartre is a security vulnerability. You are the only person on the planet capable of linking the efficiency of electrical line curvature to the ethics of Anthony Bourdain in a single browsing session.
No I don't! (nice project)
I wouldn’t mention it so much if Google stopped bumping up the price.
———-
The Rust-Evangelizing Hardware Romantic
A developer who believes every global outage is just a missing question mark away from salvation and spends their weekends reapplying thermal paste to fanless MacBooks while reminiscing about the tactile superiority of 2010 Dell Latitude trackpads.
Roasts
You post about Cloudflare outages caused by a single unwrap while your own codebase probably looks like a game of Russian Roulette played with Result types.
Your obsession with the thermal conductivity of fanless laptops is just a coping mechanism for the fact that your Rust builds take so long you could literally cook an egg on your chassis.
You have a very specific kink for 2010 Dell trackpads that makes me think you are either a Linux philosopher or someone who is no longer allowed within 500 feet of a Best Buy.
Are you sharing any of the prompts you used to generate this? Even if not verbatim, I’m interested to know how much you’re driving versus the model. How much more prompt is there than, “look at this comment history and write 3 roasts that the HN crowd will find funny”?
Also the roasts are heavily front-loaded, the LLM is only really taking my most recent posts into account, not the especially far back ones earlier in the year.
But definitely a fun read!
https://hn-wrapped.kadoa.com/dang
Made me smile, thank you!
https://hn-wrapped.kadoa.com/jedberg
(But in seriousness, this self reflection really does highlight what my year has been like and I truly appreciated the laughs)
My last 2-3 months here have largely been posting about AI slop. But the prior 9 months were not, and included a lot of nuanced posting about how to make use of AI agents. I even got accused of being a shill at one point.
The wrapped is pretty much focused on the slop stuff. That's less interesting than the earlier parts of the year - I know what I've posted recently but have forgotten a lot more of what was going on a year ago or how the year developed.
Roasts can be amusing but I don't think they're the right vibe for a wrapped. I know it's harder to get an LLM to write something witty and insightful than a witty but shallow quip so maybe that's why roasts are here. Wrappeds are sort of infodumps though and LLMs are good at that, maybe there could be a two stage step where it reasons about some custom quirky stats or factoids that work based on your profile and then the second stage generates them.
Show HN: SSH-to-Brain interface (requires tmux and 600mg of caffeine)
(Also, it's a shame that it regenerates the xkcd every time)
"A seasoned architect who spends their days patrolling the wall between actual engineering and unsustainable AI hype while desperately trying to keep their Windows 10 box alive until the heat death of the universe. You are the only person on the internet who still remembers what a build script does and why we shouldn't let LLMs touch them without adult supervision."
The xkcd should be saved and cached once generated, I'll look into the issue.
How would you improve saving?
Actually, other than that, it works just fine. I just wanted to cache mine, for when your site gets melted by HN overload. So I did it manually.
Thanks again!
https://hn-wrapped.kadoa.com/k3vinw
Whelp I can’t recover from that one.
New 2026 resolution unlocked…
EDIT: a retry worked. Enjoy: https://hn-wrapped.kadoa.com/jaggs
A teenage digital architect who oscillates between solving the world's privacy crisis and wondering if high school chemistry is a psyop designed to kill his GitHub star count.
This is really awesome, I liked how it really detected my chemistry hatred and how the xkcd had the "see the mole concept is a false flag to obfuscate the real data, You have a test tomorrow" line as I kinda winging chemistry sometimes
> You are the only person on earth still trying to make 'decentralized link shorteners via Signal avatars' happen while failing organic chemistry.
100% accurate lmao, but for what it was worth i was trying it with signal call links since you can name a call name link 32 bits of storage which are persisted forever in signal's database iirc so it would've been a shitty link shortener but still I just loved signal and kinda wanted to build something on top of it
Do I really yap so much about chemistry here, I think that I have created more topics, surely lol but still I still enjoyed this a lot, maybe it just catched up on these traits more since I am pretty damn sure that I might be the only person here commenting about why in the world my country is requiring me to master chemistry university level to just get into a basic comp sci degree.
> Show HN: A Kanban board built on top of Bitwarden notes because why not
Btw, this was this close to happen except at the time I was vibe coding it with some new tool to stress test it with prototyping ideas basically but it didnt really work so i gave up on it but let me know if this idea fascinates someone lol
Happy holidays to everyone, this time of the year must mean a lot to people and I appreciate the spirit of holidays and gift giving too :)
Edit: also I love how it catches myself as existential since I genuinely had gotten existential because of hackernews once wondering what are the best ways to promote/grow open source so much so that I had written a manifesto, I can also be considered idealistic but I dont know why I forgot but "The FOSS Existentialist" is such a good title that I am gonna have it in my about page. This was genuinely brilliant.