Live data from Hacker News

Viewing profile — alexhans

alexhans

HN member
Joined
Tue, Apr 11, 2023, 2:12 PM UTC
HN karma
118
Public activity
113 items

About alexhans

alexhans.github.io (blog)

https://ai-evals.io (community site for eval-driven development as a shared language for product building)

Recent public activity

  1. comment
    Comment #49179706

    You can also use PI with local models like Qwen3.5-35B-A3B [1] and they can be surprisingly good if you development in minimalistic/simple ways. One game changer when it comes to t…

  2. comment
    Comment #49142116

    Skills represent a pattern many of us converged to before it was named as such (very useful for comms): Progressive disclosure, determistic scripts bundled (not just markdowns). Se…

  3. comment
    Comment #49046133

    I could but I'd probably miss the angle that is helpful to you. Do you want to instead share what your pain points are, what are you trying to delegate to AI and what you aren't? B…

  4. comment
    Comment #49043351

    I'm a broken record but with: - evals - limiting AIs to tool calling, bounded planning, interpreting/producing natural language. - bounding non determinism - investing in small too…

  5. comment
    Comment #48988237

    If you actually are interested in understanding what I said, you can look at these links: - https://en.wikipedia.org/wiki/Fear,_uncertainty,_and_doubt - https://www.theregister.com…

  6. comment
    Comment #48981821

    Every Linux user or FOSS enthusiast knows the acronym FUD: Fear, Uncertainty and Doubt, which were a set of techniques commonly used to disparage efforts of open source communities…

  7. comment
    Comment #48968657

    Many of us were saying it a year ago but now with model restrictions (e.g. fable) and pricing changes it should be obvious to people that part of the economics is avoiding vendor l…

  8. comment
    Comment #48879948

    Got it. Different audience. Cool stuff. I'll take a better look as soon as I can.

  9. comment
    Comment #48873889

    I've helped people get into programming face to face and also in a site I liked called exercism which also had a multi language track unit test passing style which I really value a…

  10. comment
    Comment #48854273

    Having a thin python/ts orchestrator and workers that pick up tasks from the directories like events and decide whether to make deterministic calls and wait is pretty standard albe…

  11. comment
    Comment #48852498

    I can understand someone being overwhelmed and not wanting to configure and "build your own pi" which is really one of the beautiful points of pi, but like with vim, I do recommend…

  12. comment
    Comment #48849854

    > What's the consensus today on codex vs claude code, does it really matter anymore? Consensus is probably the wrong word for the popular opinions reflected in HN that you might ge…

  13. comment
    Comment #48758052

    Touch typing essentially. It's such a comfortable way to work. Remapping mode switching to something like jk instead of Esc is vital to stay comfortably in the home row. I always l…

  14. comment
    Comment #48678501

    Fun, responsive and intuitive. Congrats.

  15. comment
    Comment #48665909

    I guess it depends on what your exact hypothesis is Vs mine. For at least 6 years we've had AC worthy temps.

  16. comment
    Comment #48662068

    The way eval startup is defined here is very specific and doesn't cover successful eval farmwork/SaaS vendors like Arize, Promptfoo, deepeval, etc The author does have a point arou…

  17. comment
    Comment #48656390

    I'd argue that these temperatures are not a new thing. It's just a contradiction that is almost a tradition at this point, imho.

  18. comment
    Comment #48654313

    Living in London and Dublin, what I've observed is that we get the following contradictory statements: - "We don't need AC, It's only hot a few times during the year." - "Oh what a…

  19. comment
    Comment #48626954

    Exactly. I'm very happy the discourse has moved on from "but X model is the best" to "you can use open models". Whether you're using SDK or harness based agents, having evals means…

  20. comment
    Comment #48592754

    It's always satisfying when customer rights stories have a known positive outcome. The timeline is unfortunately quite slow and bureocractic but I'm glad OP managed to find out abo…

  21. comment
    Comment #48551753

    I think the criticism is constructive. It's really not about hating. I'd wager many of the people who convey this criticism do use AI to aid their writing as well. It's just that t…

  22. comment
    Comment #48551707

    Agreed. The post looks great. The story is great but the AI style in this case does distract. I'm not against using AI for writing at all but you want to be careful that the output…

  23. comment
    Comment #48520097

    I think it's important to be able to do both so you can stay in control of the price to value created relationship. In last year, some people were publishing aider /ollama/open rou…

  24. comment
    Comment #48503194

    The Foil Arms & Hog 12 year old skit [1] is still relevant. - [1] https://youtu.be/Id-zzOGnN6A (Website part at 1:42 calling out the insurance example).

  25. comment
    Comment #48395673

    I was a fan of Seven Languages in Seven Weeks [1] because it exposed you to different paradigms which you could then try to apply where they made sense on whatever tools you were u…