HNHacker News
TopNewBestAskShowJobs

Falimonda

184 karma · joined September 26, 2022

LinkedIn: https://www.linkedin.com/in/falimonda

https://convergence-frontier.com

submissionscomments
Falimonda··on Ask HN: What did you find out or explore today?
Now you can say "Me defiendo" when asked how much Spanish you speak :)
Falimonda··on AI coding tools can reduce productivity
Copilot is going to feel "amazing" at helping you quickly work within just about any subject that you're not already an expert in.

Whether or not a general purpose foundation model for coding is trained on more backend or frontend code is largely irrelevant in this specific context.

Falimonda··on Not So Fast: AI Coding Tools Can Reduce Productivity
It's moreso that a backend developer can now throw together a frontend and vice-versa without relying on a team member or needing to set aside time to internalize all the necessary concepts to just make that other part of the system work. I imagine even a full-stack developer will find benefits.
Falimonda··on Launch HN: K-Scale Labs (YC W24) – Open-Source Humanoid Robots
As much as DoD might like expensive toys, they have better options than an open-source project.
Falimonda··on Fei-Fei Li: Spatial intelligence is the next frontier in AI [video]
As someone who hasn't had to own a car in over 8 years (lived in NYC) and recently bought a 2023 Hyundai Santa Fe with birdseye view parking it shocks me how uncalibrated my car-prioception is.

It's made me realize that objects are much further from the boundaries of my car when backing into a spot parallel parking. I would never think to get so close to another car if I had to only rely on my own senses.

With that said, I realize there's a significant number of people that are even poorer estimators of these distances than myself. I.e. those that won't pass through two cars even though to me it's obvious that they could easily pass.

I have to imagine a big part of this has to do with risk assessment and lack of risk-free practice opportunity IRL. Nobody is seeing how far they can push or train themselves in this regard when the consequences are to scratch up your car and others' cars. With the birdseye view I can actually do that now!

Falimonda··on Show HN: System Prompt Learning – LLMs Learn Problem-Solving from Experience
How do you forsee a system like this efficiently managing and relying on a set of strategies whose size can become unbounded?
Falimonda··on Ask HN: What are you working on? (May 2025)
Ingesting idea! I've been looking for an alternative to using Android's Tasks app for jotting down thoughts. I prefer it over the Notes app because I can curate categories as different lists.

Random callout: the copy in your app store preview images would benefit from some proof reading. Example: "WE dont just store thoughts, but makes sense of them" should likely be "ThoughtCatcher doesn't just store thoughts, it makes sense of them". My 2 cents is to also rework "Capture your mind" as it's a little awkward. Maybe "Organize your thoughts", "Supercharge your thoughts", or something along those lines.

Falimonda··on Claude 4
Have you tried a package like LiteLLM so that you can more easily validate and switch to a newer model?

The key seems to be in curating your application's evaluation set.

Falimonda··on My new deadline: 20 years to give away virtually all my wealth
What do you believe are his motives?
Falimonda··on I'd rather read the prompt
And you do what with the prompt once you have it?
Falimonda··on Lessons from Building a Translator App That Beats Google Translate and DeepL
I'm working on a natural language router system that chooses the optimal model for a given language pair. It uses a combination of RLHF and conventional translation scoring. I envision it to soon become the cheapest translation service providing the highest average quality across languages by striking a balance between Google Translate's expensive API and any given, cheaper, random model's performance across different languages.

I'll beginning to integrate it into my user-facing application for language learners soon: www.abal.ai

Falimonda··on Business co-founders in tech startups are less valuable than they think
A good rule of thumb I picked to from Founders at Work is that the idea person gets a 5% bump on equity, but no more than that.
Falimonda··on AI Coding assistants provide little value because a programmer's job is to think
I was rooting for the strawberry. You delivered!
Falimonda··on AI Coding assistants provide little value because a programmer's job is to think
There's nothing natural about using emacs in the way that an LLM can convert natural language to working code and productivity gains.

For better or worse, you won't find correctness on any business' income statement. Sure, it's a latent variable, but so is efficiency.

Falimonda··on AI Coding assistants provide little value because a programmer's job is to think
I've experienced gemini get stuck as you describe a handful of times. With that said, my predication is made on the observation that these tools are already force multipliers, and they're only getting better each passing quarter.

You'll of course be free to use them optionally in your free time and on personal projects. It won't be the case at your place of employment.

I will mark my calendar!

Falimonda··on AI Coding assistants provide little value because a programmer's job is to think
I fear this will not age well.

Which models have you tried to date? Can you come up with a top 3 ranking among popular models based on your definition of value?

What can be said about the ability of an LLM to translate your thinking represented in natural language to working code at rates exceeding 5-10x your typing speed?

Mark my words: Every single business that has a need for SWEs will obligate their SWEs to use AI coding assistants by the end of 2026, if not by the end of 2025. It will not be optional like it is today. Now is the time you should be exploring which models are better at "thinking" than others, and discerning which thinking you should be doing vs. which thinking you can leave up to ever-advancing LLMs.

Falimonda··on OpenAI releases image generation in the API
The model they're training to perform detection/identification out in the field would presumably need to be much smaller and run locally without needing to rely on network connectivity. It makes sense, so long as the openai model produces a training/validation set that's comparable to one that their development team would otherwise need to curate by hand.
Falimonda··on MCP on AWS Lambda with MCPEngine
As just one example, SaaS businesses are beginning to use this to reduce the barrier to entry for their users, which is always the first step to the ultimate goal: a programmatic integration.

This is especially true for conventional SaaS that historically required one or more developers to read and internalize documentation for a service's API in order to make any use of it.

What are the odds that this developer fully understands how to squeeze every bit of value of out this expensive SaaS product, for which the company is paying monthly/yearly?

What if that developer jumps ship? Or the provider releases a major version bump with a significantly different API, but features that the business absolutely needs to integrate in order to stay ahead?

As much as it might seem hyped up at the moment, MPC and agent-based tool calling paired with CoT can and will make things orders of magnitude more efficient.

No business in its right mind will accept anything less than the total integration of MCP and agents across their entire stack by the end of this year.

Falimonda··on Why is OpenAI buying Windsurf?
Yeah, it is! SWE in a professional setting is changed for ever whether people like it or not.

No sane organization will accept anything less than forcing SWEs to use these tools moving forward. The details might differ and some will delay because "IP", but they'll all converge very quickly.

Not to say there's no joy in doing it the old-fashioned way on your own time :)

Falimonda··on Why is OpenAI buying Windsurf?
I've only used it with Cursor.

I've seen the light!

Falimonda··on Why is OpenAI buying Windsurf?
Agentic flows will soon overtake auto-complete. Models like claude sonnet 3.5 were already good enough, albeit requiring the user to actively limit context length.

Most recently, gemini 2.5 pro makes the agentic workflow usable, and how!

Falimonda··on Show HN: I built a Yahoo Messenger-inspired web chat app – pure nostalgia
a/s/l?

also, will I be able to play pool?

Falimonda··on ABAL: All Books, All Languages
Good eye! Thank you.
Falimonda··on ABAL: All Books, All Languages
I agree it's far from perfect. In addition to the existing "beta" label, I'll consider adding a disclaimer/warning to users that the system is still in beta and will suffer from inaccuracies in translation.

What am I doing to fix this long term?

I'm currently building an optimization mechanism to ensure the highest quality translations for any given language pair.

I really appreciate your detailed feedback. Do let me know if anything else comes to mind.

Falimonda··on ABAL: All Books, All Languages
"All Books, All Languages", or ABAL for short, is a modern, web-based, parallel text language-learning application that I've been working on as a side project for about a year. I've already received a lot of great feedback about the application among language learners. In addition to what I hope is an intuitive UI/UX, one of the unique things about ABAL is the way that pronunciations are customized to a user's native and target languages.

Systems like IPA (https://en.wikipedia.org/wiki/International_Phonetic_Alphabe...) don't make pronunciation any easier to get right for a majority of - if not all - language learners. ABAL solves this by showing phonetic hints that are written in the user's native language script and are meant to be pronounced in the native language's voice.

The name All Books, All Languages is intentionally quixotic, as it serves to set the ambitious and unreachable goal of hosting all of humanity's written works while making them available to all language learners and readers across the globe!

Today, it hosts a number of generated short stories categorized by subject and CEFR level. I'm currently working on supporting (private) self-uploaded files, and works in the public domain. Work is also going into adding support for more languages, while evaluating and optimizing for cross-language translations accuracy.

It currently supports 56 languages (including Klingon and Latin!) - which comes out to 3080 permutations - or 3080 unique user profiles as I like to think of it. Both the marketing and application sites are fully internationalized - even response messages in 4xx responses use i18n. Quite a bit of work went into automating the i18n diff generation system to make sure I can release UI/UX changes quickly.

I hope you'll find it useful if you're learning a new language or need to practice one you already know. If you're not learning a new language, but wish you could read classics in a language you're fluent in, stay tuned!

Falimonda··on AI 2027
We'll be lucky if "World peace should have been a prerequisite to AGI" is engraved on our proverbial gravestone by our forthcoming overlords.
Falimonda··on Show HN: All Books, All Languages – Read short stories and books in any language
I'm glad to hear that! Do let me know if you have any feedback on it.
Falimonda··on Show HN: All Books, All Languages – Read short stories and books in any language
I generated category levels and subcategories first. These are associated to a CEFR level and all that bundled into the story generator.

While it's currently decent for the purpose of language learning, I do need to fix consistency across longer stories because a purely sequential generation suffers from consistency in plot details.

The idea was always to offer real books in the public domian, but I decided to release it with generated stories so I could begin gather feedback on UI/UX.

Thanks for calling that out! I'll look into it.

Falimonda··on Male octopus injects female with venom during sex to avoid being eaten
What local maxima might humans be stuck in?
Falimonda··on DARPA exploring growing bio structures of "unprecedented size" in microgravity
Can we / will be ever be able to grow bioengineered coral at an accelerated rate with a desired growth structure/direction in space?
← PreviousPage 3 of 6Next →