misterchocolat
Re:Why Common Lisp Is Now the Best Programming Language
on Tuesday October 06, 2026 @12:54AM (#49974349)
Thanks!
I've seen a big improvement in LLMs writing macros since Opus 5.5 came out. What really helps I think is that I've written skill files with my own examples and instructions.
Same thing for image-based dev. without an agent.md file with good instructions on how to work with a live image it will do dumb things. this sort of workflow is jsut so far off the training distribution.
I think what changed recently isn't that LLMs got better at CL, they just got way better at taking my skill/agent.md files and reasoning through them.
Re:Why Common Lisp Is Now the Best Programming Language
on Tuesday October 06, 2026 @12:45AM (#49974300)
Fair enough haha you got me
Re:Why Common Lisp Is Now the Best Programming Language
on Tuesday October 06, 2026 @12:26AM (#49974182)
I mean if we're heading towards a future where code gen gets super cheap and super good what stops you from porting the libraries you want?
Re:Why Common Lisp Is Now the Best Programming Language
on Tuesday October 06, 2026 @12:20AM (#49974137)
sure I agree the LLM doesn't need a DSL to get work done. The point is more that the DSL holds the opinions of whoever built the product
Re:Why Common Lisp Is Now the Best Programming Language
on Monday October 05, 2026 @10:59PM (#49973637)
Happy to discuss
Re:Plunging test scores are a slow-moving catastrophe
on Sunday September 27, 2026 @09:50AM (#49866640)
Did I ever use the term "Orwellian" in my comment?
Re:Plunging test scores are a slow-moving catastrophe
on Saturday September 26, 2026 @12:11PM (#49857893)
Orwell's 6 rules for good writing:
1. Never use a metaphor, simile, or other figure of speech which you are used to seeing in print.
2. Never use a long word where a short one will do.
3. If it is possible to cut a word out, always cut it out.
4. Never use the passive where you can use the active.
5. Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent.
6. Break any of these rules sooner than say anything outright barbarous.
Now you tell me
Re:Plunging test scores are a slow-moving catastrophe
on Saturday September 26, 2026 @11:42AM (#49857591)
Holy sentence... George Orwell must be turning in his grave right now.
Show HN: Vsqrd – AWS for Biology Experiments
Hi hn. We built VSQRD, which is a place to order and run outsourced preclinical studies.Right now biotechs that outsource studies to CROs (contract research organizations) have to find them manually. That makes it hard to find the right expertise at the right price.But hey it doesn't have to be this way!! We built vsqrd.com, where CROs can list their study offerings and biotechs can compare and...
Re:Launch HN: Risklytics (YC S26) – Insurance brokerage for frontier t...
on Wednesday August 26, 2026 @01:22PM (#49452711)
Actually a great idea, wishing you guys success.
Re:Show HN: Palmier Pro – open-source macOS video editor built for AI
on Thursday July 23, 2026 @02:15PM (#49025867)
I've been following Marcos's youtube channel and it's so great to see that they've finally found their thing. Looks like an awesome product that people actually want. Well done.
Framework for building agent-friendly CLIs
2H barrier broken in London marathon
Is anyone actually using OpenClaw?
I don't use it personally, and neither does anyone in my circle...even though I feel like I'm super plugged into the ai world
Show HN: Bound – local code autocomplete LLM fine-tuned on your repository
Hi everyone, I'm Vivien one of the creators of Bound.I'll keep things brief, there are two things I hate about using AI coding models: paying a subscription and how bad they are for the environment.So my cofounder and I built Bound. Simply put, we provide Cursor's "tab" feature but instead of using a cloud model we use an ultra-small local LLM trained on your own repo (that and a couple other...
Re:Lessons from 14 Years at Google
on Sunday January 04, 2026 @12:31PM (#46490134)
that was an amazing read
Re:Show HN: Stop AI scrapers from hammering your self-hosted blog
on Friday December 19, 2025 @08:53AM (#46325861)
didn't know that thanks for pointing it out, i'll remove that feature
Re:Show HN: Stop AI scrapers from hammering your self-hosted blog
on Thursday December 18, 2025 @04:07PM (#46318736)
the parent container uses display: none, so a screen reader will skip the links
Re:Show HN: Stop AI scrapers from hammering your self-hosted blog
on Thursday December 18, 2025 @05:50AM (#46311134)
hey! thanks for that read suggestion that's indeed a pretty funny captcha strat. Yup the links show up if you use the Lynx web browser. As for AI scrapers impersonating googlebot I feel like yes they'd definitely start doing that, unless the risk of getting sued by google is too high? If google could even sue them for doing that?
Not an internet litigation expert but seems like it could be debatable
Re:Show HN: Stop AI scrapers from hammering your self-hosted blog
on Tuesday December 16, 2025 @07:37PM (#46296767)
yes but here it's free, whereas this (https://webdecoy.com/) is at least 59$ a month
Show HN: Stop AI scrapers from hammering your self-hosted blog
https://github.com/vivienhenz24/fuzzy-canary
Alright so if you run a self-hosted blog, you've probably noticed AI companies scraping it for training data. And not just a little (RIP to your server bill).There isn't much you can do about it without cloudflare. These companies ignore robots.txt, and you're competing with teams with more resources than you. It's you vs the MJs of programming, you're not going to win.But there is a solution....
I think series.so is a fraud? [video]
Re:Cognitive Dissonance
on Tuesday September 23, 2025 @12:34PM (#45349376)
Most of the Trump supporters I showed it to were well-educated and from what I could tell were very much in touch with what is going on in the world. I feel like they just don't want to "see".
Re:Cognitive Dissonance
on Tuesday September 23, 2025 @12:25PM (#45349222)
The reactions to the essay are way more interesting than the essay itself: when "liberals" read it, they immediately get that it's about Donald Trump. But when Trump supporters read it, almost all of them go "yeah good points, but why did you write about Hitler?".
Are we doomed?