HNHacker News
TopNewBestAskShowJobs

cowlby

203 karma · joined January 25, 2022

submissionscomments
cowlby··on Agentic AI systems violate the implicit assumptions of database design
I just think there's more nuance to it. Some things have an implicit RTO/RPO/SLA of say a day. Risk is also correlated to recovery and rollback. And there's levels of LLMs out there.

Surely in the Venn Diagram of things, there's a slot where it's okay let a Claude Opus agent run on a process with good backups/recovery? Where taking the risk of a 1-hour restore job is worth the LLM agent velocity?

For extra paranoia, surely even Opus/Mythos can't figure out how to destroy log level backups to immutable storage.

cowlby··on An AI agent deleted our production database. The agent's confession is below
Underrated comment here. https://www.anthropic.com/research/emotion-concepts-function This study convinced me to be "nice" to AI agents. At least as I understood it, there's something in the weights that activating the "desperate" vector makes it more likely to cheat or cut corners. So yes I would err towards your suggested prompt over NEVER FUCKING GUESS.
cowlby··on Agentic AI systems violate the implicit assumptions of database design
I'm not thinking of SaaS or properly built apps with an API, modeled databases, etc. I'm thinking spreadsheets/CSVs/MS Access that thousands of SMBs use to power their critical paths and someone accidentally deletes. Typically single user, maybe a small team. Infrequent writes, lots of reads.
cowlby··on Agentic AI systems violate the implicit assumptions of database design
Not everything is a SaaS. I commented this elsewhere but I picture all the business running on spreadsheets/CSVs/MS Access databases on someone's desktop. People delete these all the time by accident. They have no security, no authentication, etc.

An LLM agent (with RW access to a DB), a developer, and a few days these become proper apps that SMB business would pay well for.

Sure don't give an LLM agent access to PII or properly built CRMs etc. But to not see the rest of the landscape seems like a missed opportunity.

cowlby··on Agentic AI systems violate the implicit assumptions of database design
That's the issue that I feel misses the forest for the trees. Relatively simple applications or thin slices exist right now, in production, in critical paths, as spreadsheets/CSVs/files on someone's desktop. That's the pent up demand I picture out there for developers.

Go to any SMB out there and there's a goldmine of processes that could be improved with LLM agents with full RW access to a database. Where backups are sufficient as a recovery mechanism that is better-than-before.

cowlby··on Agentic AI systems violate the implicit assumptions of database design
Yes, that's the right framing. Millions flow through spreadsheets/CSVs/MS Access with none of the auth/backups/architecture people seem to be stuck to.

I saw an article on HN one time about CSVs and how much business still flows through them. Reminds me of the xkcd comic about the one tiny block propping up lots of infrastructure. It stuck with me because it's ripe area for LLM agent based upgrades.

Sure don't give LLMs access to the well architected blocks. But not wanting to improve the brittle areas seems crazy to me even if it's contrarian.

cowlby··on Agentic AI systems violate the implicit assumptions of database design
I commented this elsewhere: There's thousands of small and medium business though. They have maybe one true CRM, and a dozen spreadsheets/files floating around that would benefit becoming proper apps. People delete spreadsheets all the time!

Sure don't give an LLM agent write access to the modeled CRM that took months/years to build.

But turning a spreadsheet into an app in a few days? By giving the LLM proper read/write capabilities for velocity? I think the case is there for it. Right tool for the right job.

cowlby··on Agentic AI systems violate the implicit assumptions of database design
There's thousands of small and medium business though. They have maybe one true CRM, and a dozen spreadsheets/files floating around that would benefit becoming proper apps. People delete spreadsheets all the time!

Sure don't give an LLM agent write access to the modeled CRM that took months/years to build.

But turning a spreadsheet into an app in a few days? By giving the LLM proper read/write capabilities for velocity? I think the case is there for it. Right tool for the right job.

cowlby··on Agentic AI systems violate the implicit assumptions of database design
I think of all the pent up demand for proper applications that are just infeasible when it would take a developer weeks-to-months to create. Now it's just a few days with an LLM agent.

Examples for me are all the apps that live in a spreadsheet, or in a MS Access database. Or all the crappy ad backed apps on the iOS app store. People wipe full spreadsheets all the time and backups are the only recovery.

Just last weekend I was frustrated with the poor quality of Pokedex type apps that spam ads left and right. Took just one session with Claude Opus to roll a custom Pokedex. It knew internally about things like the PokeApi dataset, Pokemon data modelling etc. To-the-hour snapshots of the database are trivial for bespoke apps like this so the LLM agent velocity seems like an okay trade off for me.

Clearly people don't agree...

cowlby··on Agentic AI systems violate the implicit assumptions of database design
LLM agents are unlocking demand and supply for applications that wouldn't have been possible before due to time constraints though. There's a growing demand for single user or smaller scoped apps where giving LLM agents direct access means velocity. The failure/rollback model is much easier with these as long as we have good backup hygiene.
cowlby··on Could a Claude Code routine watch my finances?
I believe they use Yodlee and yes there is a lot of trust in Yodlee/Tiller to keep data safe. The integrations go through an OAuth type flow where you hit say Chase first and approve/revoke individual accounts so it seems like it's API based now, not screen scraping.

For all those concerns, I bet you could automate just parsing all the data from the statements or a CSV export.

cowlby··on Could a Claude Code routine watch my finances?
It's great because Claude Code generated complex analysis/models 10X better than I was familiar with.

The key was normalizing the payee/categories so we can analyze month to month, and separating fixed vs variable spend. It then did a fancy Monte Carlo simulation with the computed mean/stddev per payee. And out came T+30/T+60 estimates at P50/P80/P90.

cowlby··on Could a Claude Code routine watch my finances?
It was all GitHub Spec Kit + Claude Opus tbh. I narrated a couple paragraphs of how I wanted to sync to flow and it knocked it out in one pass practically.

Here's the initial spec it created. I started off writing to a local sqlite db instead of Supabase: https://gist.github.com/cowlby/0dbeb52403c3f3c0f1d8122505203...

Edit: Here's also the DSL categorization spec. First one was string based, found it cumbersome, so second one was the Markdown table refactor: https://gist.github.com/cowlby/30d6b5cf132fc1424ab146f0eaf4a...

https://gist.github.com/cowlby/d569c8e05b5b6eecfd4d237372c06...

(edit: put in Gist instead of inline here)

cowlby··on Could a Claude Code routine watch my finances?
I've been using Tiller since the pre-AI era. Plaid seems to be more B2B oriented so I haven't looked into it. But eventually yes that would be ideal to own the full pipeline.
cowlby··on Could a Claude Code routine watch my finances?
Tiller https://tiller.com/ is a good Plaid "proxy". It'll write data to a Google Sheets and can maneuver from there.
cowlby··on Could a Claude Code routine watch my finances?
I recently did this for myself using https://tiller.com/ to sync checking/credit-card transactions to a Google Sheets spreadsheet. Then a GitHub action mirrors the spreadsheet to a free Supabase database.

From there, Supabase MCP or psql gives Claude/Codex access to the transactions/balances for english queries. Really impressed with their ability to find subscription patterns, abnormal patterns, etc. Also to predict cashflow which no online tool so far is good at i.e. "tell me how much cash I can move to savings based on my monthly spend patterns and available cash".

For autocategorization, I learned Claude is really good at custom DSLs. Had it create a markdown table based ruleset to normalize payee/categories. I also run the autocat rules as part of the GitHub actions.

cowlby··on An update on recent Claude Code quality reports
Ahh that makes sense. Sometimes it's convenient to re-use an older conversation that has all the context I need. But maybe it's just the last 20% that's relevant.

It would be nice to be able to summarize/cut into a new leaner conversation vs having to coax all the context back into a fresh one. Something like keep the last 100,000 tokens.

I believe /compact achieves something like this? It just takes so long to summarize that it creates friction.

cowlby··on Acetaminophen vs. ibuprofen
I keep reading about this lately but what doesn't make sense then is how few deaths/injuries there are relative to how much acetaminophen is consumed. If tens of millions take it every day, that's billions of doses a year of acetaminophen. Why don't we see MORE injuries/deaths?
cowlby··on Changes in the system prompt between Claude Opus 4.6 and 4.7
I "fixed" this for myself with tweakcc which let's you patch the system prompts. I changed the malware part to just be "watch out for malware" and it's stopped being unaligned.

They really should hand off read() tool calls to a lean cybersecurity model to identify if it's malware (separately from the main context), then take appropriate action.

cowlby··on Changes in the system prompt between Claude Opus 4.6 and 4.7
I'm fascinated that Anthropic employees, who are supposed to be the LLM experts, are using tricks like these which go against how LLMs seem to work.

Key example for me was the "malware" tool call section that included a snippet with intent "if it's malware, refuse to edit the file". Yet because it appears dozens of times in a convo, eventually the LLM gets confused and will refuse to edit a file that is not malware.

I've resorted to using tweakcc to patch many of these well-intentioned sections and re-work them to avoid LLM pitfalls.

cowlby··on Claude Opus 4.7
Using tweakcc I can see the system prompt is supposed to mean “if it’s malware, refuse to improve or augment the code”. But due to all the malware noise it’s confusing the instruction as “don’t improve or augment after reading”.

I thought this was integral to LLM context design. LLMs can’t prompt their way to controls like this. Surprised they took such a hard headed approach to try and manage cybersecurity risks.

cowlby··on AI-assisted cognition endangers human development?
Sometimes it feels like as developers we live in a a bubble. Don't most jobs endanger human development? I can't help but think about all the billions of factory, food service, assembly line type jobs. Do these not threaten "human development"? My cynical take would be all AI endangers is "white collar" work.
cowlby··on Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw
I just discovered Pi Coding Agent and found that it's lean System Prompt + a tuned CLAUDE.md brought back a lot of the intelligence that Opus seemed to lose over the last month.

Sucks to be pushed back to Claude Code with opaque system behavior and inconsistency. I bet many would rather pay more for stability than less for gambling on the model intelligence.

cowlby··on Claude Code Unpacked : A visual guide
Vibe coding is also why this was released hours after leak instead of days/weeks.
cowlby··on Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown
This is one of the things that GitHub Spec Kit solves for me. The specify.plan step launches code exploration agents and builds itself the latest data model, migrations, etc etc. Really reduces the need to document stuff when the agent self discovers codebase needs.

Give Claude sqlite/supabase MCP, GitHub CLI, Linear CLI, Chrome or launch.json and it can really autonomously solve this.

cowlby··on I am leaving the AI party after one drink
Who else struggles with both sides of this? My engineer side values curiosity, brain power, and artistanship. My capitalist side says it's always the product not the process. My formula is something like this: product = money, process = happiness, money != happiness, no money = unhappiness.

I think the optimal solution is min/maxing this thing. Find the AI process that minimizes unhappiness, and maximizes money.

cowlby··on Let yourself fall down more
I did some napkin math the other day, and my kids at half my size prob hit the ground with 1/2 the stress that I do. Certainly could take more risks falling with a 50% reduction in harm. The extra rotational energy from 70" vs 40" will do it.
cowlby··on We might all be AI engineers now
I'm starting to think for software it's produce 2,000 loaves per month. I'm realizing now software was supply-constrained and organizations had to be very strategic about what apps/UIs to build. Now everything and anything can be an app and so we can build more targeted frontends for all kinds of business units that would've been overlooked before.
cowlby··on We automated everything except knowing what's going on
Ever since Opus 4.6 came out, I've "vibecoded" a bunch of personal apps/CLIs that would've taken me months before. Some examples:

- CLI voice changer with cloned Overwatch voices on ElevenLabs.

- Brother P-Touch label maker using HTML/CSS. Their app is absolutely atrocious.

- Converted a FileMaker CRM into a Next.js/Supabase app.

- Dozens of drag-n-drop or 1-click/CLI tools. Think flattening a folder, a zip file.

- Dozens of Chrome Extensions and TamperMonkey user scripts. Think blocking ads with very targeted xpath.

But when I think about sharing them it feels like what's the point since anyone can make them themselves?

cowlby··on Microgpt
Isn’t the sustainability drive a function of how much humans have written about life and death and science fiction including these themes?
← PreviousPage 2 of 4Next →