HNHacker News
TopNewBestAskShowJobs

mercurialsolo

226 karma · joined March 22, 2020

Building cabal
submissionscomments
mercurialsolo··on Claude Skills
One sharp contrast though I see between OpenAI and Anthropic is the product extensions are built around their flagship products.

OpenAI ships extensions for ChatGPT - that feed more to plug into the consumer experience. Anthropic ships extensions (made for builders) into ClaudeCode - feel more DX.

mercurialsolo··on Claude Skills
Sub agents, mcp, skills - wonder how are they supposed to interact with each other?

Feels like fair bit of overlap here. It's ok to proceed in a direction where you are upgrading the spec and enabling claude wth additional capabilities. But one can pretty much use any of these approaches and end up with the same capability for an agent.

Right now feels like a ux upgrade from mcp where you need a json but instead can use a markdown in a file / folder and provide multi-modal inputs.

mercurialsolo··on Instant Checkout and the Agentic Commerce Protocol
This is a new amazon marketplace with trusted reviews. IMO having worked in commerce for a while - this opens up new avenues for merchants to work on gaming reccomendations and the trust quotient delivered.

It also opens up - ads - subscriptions - transactions

based revenue lines for OpenAI

mercurialsolo··on Claude Code 2.0
/rewind was a must needed upgrade for the agent.

- Need better memory management and controls (especially across multi-repos) - /upgrade needs better management

mercurialsolo··on California governor signs AI transparency bill into law
Quis custodiet ipsos custodes?
mercurialsolo··on Death rates rose in hospital ERs after private equity firms took over
Why does this sound like a Boeing 2.0? Hand over to the sharks and you see incidents go up
mercurialsolo··on The Theatre of Pull Requests and Code Review
This seems a lot like fragmenting context across the edit and the commit itself. With coding agents in the loop now

1. Why do you want to fragment context? Why not add this to the main file with inline docs?

mercurialsolo··on Cloudflare Email Service: private beta
Cloudflare is the new AWS
mercurialsolo··on Product Hunt is dead
Product Hunt died a few years back. Can't say it was good when it lasted.

I also wonder whether software products can be discovered through a launch any longer. Just too much noise and high throughput at which they are being released - once u get past the page all products look like they were baked by clones or a completely divergent one that needs investment.

The launch model is broken.

mercurialsolo··on Getting AI to work in complex codebases
Good pointers on decompositing and looking at implementation or fixing in chunks.

1. Break down the feature or bug report into a technical implementation spec. Add in COT for the splits. 2. Verify the implementation spec. Feed reviews back to your original agent that has created the spec. Edit, merge, integrate feedback. 3. Transform implementation spec into an implementation plan - logically split into modules look at dependency chain. 4. Build, test and integrate continuously with coding agents 5. Squash the commits if needed into a single one for the whole feature.

Generally has worked well as a process when working on a complex feature. You can add in HITL at each stage if you need more verification.

For larger codebases always maintain an ARCHITECTURE.md and for larger modules a DESIGN.md

mercurialsolo··on Launch HN: Relace (YC W23) – Models for fast and reliable codegen
Good job on the launch - will give it a spin for our coding agent. Having worked a bunch with the agents i see below as the next evolution or leap in agents.

I see 2 big factors to improve ability of coding agents today

- on device model - context (or understanding of modules) - not only retrieving the relevant sections or codebase but creating a version (transforming it) which is readily consumable by a model and used to focus on the problem at hand.

This requires both a macro global context of the codebase and the ability to retrieve the local context of the problem being solved.

Augment context e.g. does a fairly good job of context compression and retrieval among coding agents. Fast indexing & retrieval is a good step forward to enable open context compression

mercurialsolo··on Storefront Web Components
This is a master move though - it's kinda like video(youtube) embeds in your site. If every site could sell and have an infinite curated catalog from shopify merchants - shopify becomes both the discovery, distribution and the shopping network?
mercurialsolo··on Launch HN: Roark (YC W25) – Taking the pain out of voice AI testing
As someone who's building a personal work assistant for voice - I see the merit in automating test case generation and validation.

All products in this space by YC teams are targeted at scaled voice agent startups or teams.

- Roark (https://roark.ai/)

- Hammin (https://hamming.ai/)

- Coval (https://www.coval.dev/)

- Vocera (https://www.vocera.ai/)

How do you differentiate - who is this for? Voice agent devs paying $500/mo. for early stage software?

mercurialsolo··on OpenAI says it has evidence DeepSeek used its model to train competitor
How the vibe has turned on OpenAI?
mercurialsolo··on Render raises $80M in Series C financing
What are some companies or apps or teams which are fully powered by render cloud? Are they b2b or b2c ?
mercurialsolo··on Render raises $80M in Series C financing
What are some companies or apps or teams which are fully powered by render cloud?
mercurialsolo··on AI founders will learn the bitter lesson
love it when a 25 year old founder says we have been here multiple times in the past
mercurialsolo··on Salesforce will hire no more software engineers in 2025, says Marc Benioff
Is agentforce working at all? Any practical use-cases beyond the customer support one?
mercurialsolo··on Salesforce will hire no more software engineers in 2025, says Marc Benioff
Is agentforce working and are there any practical users who have got beyond the customer support use-case?
mercurialsolo··on Can LLMs Generate Novel Research Ideas?
The difference between novelty and hallucination is feasibility. With integrated critique and feasibility checks you can eventually map the hallucination space into novelty.
mercurialsolo··on Launch HN: Airhart Aeronautics (YC S22) – A modern personal airplane
Super ambitious project that you are attempting - kudos to that!

What do you think of 1. Licenses 2. Air traffic control & routing for personal crafts 3. Landing / Takeoff / Turbulence (weather) - where typically most of the human skill today is used in for commercial flights. 4. and probably the one for interface design and overall autonomous systems - human decision making + autonomous systems really have a difficult time working in tandem - fully autonomous is less risky at an aggregate level but puts onus and more of the blame on the company / maker versus human-in-the-loop.

mercurialsolo··on What we've learned from a year of building with LLMs
As we go about moving LLM enabled products into production we definitely see a bunch of what is being spoken about resonate. We also see the below as areas which need to be expanded upon for developers building in the space to take products to production :

I would love to see this article also expand to touch upon things like : - data management - (tooling, frameworks, open vs closed data management, labelling & annotations) - inference as a pipeline - frameworks for breaking down model inference into smaller tasks & combining outputs (do DAG's have a role to play here?) - prompts - areas like caching, management, versioning, evaluations - model observability - tokens, costs, latency, drift? - evals for multimodality - how do we tackle evals here which in turn can go into loops e.g. quality of audio, speech or visual outputs

mercurialsolo··on Recall: Stealing everything you've ever typed or viewed on your own Windows PC
Beyond the technology community I doubt that the loss of personal privacy is being discussed at large. Ad trackers had already made internet privacy a myth for the vast majority of the world; we now are seeing this permeate onto personal devices and subsequently to our environment with these always on, silently tracking devices - in the name of convenience.

Perfect recall, no need for memory, available at your fingertips - with T&C that completely disregards your need for personal privacy.

The challenge though is the "better" alternatives where a mix of privacy and convenience is there is not always convenient. We have and continue to be marketed convenience at the cost of privacy.

What we need is consumer data privacy to really become a societal and government concern and for devices which infringe on this to really go through the same scruity as say a drug going thru FDA approval.

mercurialsolo··on To the brain, reading computer code is not the same as reading language (2020)
We have come to see with LLM's that language can be generated by using math.

Would love to see if this is the same when reading different patterns of code - functional vs object oriented. Where do product specs or technical specs lie?

All of this feels more pseudo-science to me - the distinction between language and math is not well understood at the moment.

mercurialsolo··on Sharing details on a recent incident impacting one of our customers
Only if internal tools went thru the same scrutiny as public tools.

More often than not critical parameters or mis-configurations happen because of internal tools which work on unpublished params.

Internal tools should be treated as tech debt. You won't be able to eliminate issues but vastly reduce the surface area of errors.

mercurialsolo··on Malleable software in the age of LLMs (2023)
I call this movement the operator tool.

Tools will no longer need operators as adding multi modality to tools will ensure we can actually have the operator interface on top of the tool.

Tuning the operator is where the playing field shifts to as operators which can translate fuzzy inputs to creative specs or workflows which can in turn be executed by the downstream engine.

mercurialsolo··on Tool Use (function calling)
By the looks of it - soon we will be needing resumes and work profiles for tools and APIs to be consumed by LLM's
mercurialsolo··on I'm Too Old
I think of this as what does it mean to be human and what craft do we enjoy - does knowing that chess engines can beat most of us take away the fun of playing chess with another person. Similarily does knowing that an factory can mass produce my furniture take away the pleasure of making a chair with my hand - there will be place for both as well as there will be new kinds of chairs to be made with AI.

Hitherto we have always thought of software as one for many - the aspects of adoption of software is left to humans.

Maybe we will shift more of our skills to higher level skills - how do we make more enjoyable products rather than how do we learn the nuance of programming languages, software paradigms and we may evolve software and technical paradigms around these.

I doubt this is the age of the death of building. We will just invent and build new things.

Generative Media by AI - while dystopian can also make us think what does media really means - will there be more value on in-person media rather than digital media?

Will it also mean we have a larger spectrum of artists who can now create - not just books and blogs but multi-media experiences that are immersive worlds/moments?

mercurialsolo··on Hot takes on Devin, the AI software engineer
The ultimate goal of an organization (and society) is to disrupt itself. Then the new order becomes an evolution of the old and thus it becomes a continuity.
mercurialsolo··on Push notifications – What to push, what not to push, and how often
While we think of push more in context of notifs - this same logic can be applied to any recommendations that come over a channel where intent is to be inferred based on past behaviour versus determined based on user input - be it on email, or any messaging channel or even on a subsequent visit to a page.

While we can debate the merits/demerits of push - for practical commerce, a large part of the world still switches on push, and relevant push will deliver more concrete and better ROI.

← PreviousPage 2 of 6Next →