Hacker News: philipodonnell

New comment by philipodonnell in "Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam)"

philipodonnell — Fri, 27 Mar 2026 20:52:27 +0000

Is the difficulty that in high entropy situations, you can’t really tell whether it’s because the model is uncertain, or because of the options are so semantically similar that it doesn’t matter which one you choose? Like pure synonyms.

New comment by philipodonnell in "Training students to prove they're not robots is pushing them to use more AI"

philipodonnell — Sat, 07 Mar 2026 21:28:25 +0000

Despite being a different kind of writing, there are some interesting parallels with the article in what you wrote here

New comment by philipodonnell in "Many Small Queries Are Efficient in SQLite"

philipodonnell — Sat, 24 Jan 2026 13:05:02 +0000

I’ve been experimenting with LiveStoreJS which uses a custom SQLite WASM binary for event sync, so for simplicity I’ve also used it for regular application data in browser and found no issues (yet). It surprised me that using a full database engine in memory could perform well vs native JS objects at scale but perhaps at scale is when it starts to shine. Just be wary of size limits beyond 16-20mb.

New comment by philipodonnell in "Composing APIs and CLIs in the LLM era"

philipodonnell — Fri, 23 Jan 2026 00:36:11 +0000

Of all the interface modalities available, CLIs seem like the most natural for copilots to work with. Lots of examples in the training data, universal interface for help, maps well to the sequential nature of token generation, similar syntax for different OSs… I can see them replacing skills and MCP et al from the model’s perspective.

New comment by philipodonnell in "A lawsuit says Workday's AI shut out applicants over 40"

philipodonnell — Fri, 09 Jan 2026 22:56:12 +0000

How do they prove this? It sounds like the plaintiffs basically claimed they were rejected a bunch of times and since the resume had recognizable indicators of protected classes they must have been discriminated against?

Don’t get me wrong, I do this work, and Workdays statement of “we don’t use protected classes” instead of “we test our models to prove they are unbiased when given recognizable indicators of protected classes” is pretty telling. Because it’s hard and if you solved it you would be proud. If you don’t control for it it WILL discriminate. See Amazon’s experiment a decade ago.

I’m just really curious how all this plays out in front of a judge.

New comment by philipodonnell in "Opus 4.5 is not the normal AI agent experience that I have had thus far"

philipodonnell — Thu, 08 Jan 2026 14:00:56 +0000

You should just need the AGENTS.md right?

New comment by philipodonnell in "95% of Companies See 'Zero Return' on $30B Generative AI Spend"

philipodonnell — Thu, 21 Aug 2025 16:19:35 +0000

Anyone have a link to the actual report?

New comment by philipodonnell in "Show HN: Move to dodge the bullets. How long can you survive?"

philipodonnell — Tue, 12 Aug 2025 12:17:39 +0000

This is a great use case for using an algorithmic difficulty ramp where it can really dial in that curve to solve for getting people to play longer over multiple sessions.

New comment by philipodonnell in "Building agents using streaming SQL queries"

philipodonnell — Wed, 18 Jun 2025 17:38:36 +0000

I’ve built lots of pre-LLM data processing pipelines like this and the more I read people putting “agents” into this kind of context the less they resemble agents like the Anthropics of the world defines and the more they just resemble functions. I wonder if eventually there won’t be a distinction and it’ll just be a way to make processing and branching nodes in a pipeline less deterministic when you need more flexibility than pure code-rules can give you.

New comment by philipodonnell in "Why DeepSeek is cheap at scale but expensive to run locally"

philipodonnell — Sun, 01 Jun 2025 14:02:04 +0000

Isn’t this an arbitrage opportunity? Offer to pay a fraction of the cost per token but accept that your tokens will only be processed when the batch window isn’t big enough, then resell that for a markup to people who need non-time sensitive inference?

New comment by philipodonnell in "Ask HN: Anyone making a living from a paid API?"

philipodonnell — Sat, 31 May 2025 18:26:44 +0000

What kind of customers are using this API? I’ve had many similar thoughts but I get hung up on the idea that customers are “developers” from a marketing standpoint, because those developers are developing something and that something is probably a bigger driver of utility that a truly generically developer tool like Cursor.

New comment by philipodonnell in "In the US, a rotating detonation rocket engine takes flight"

philipodonnell — Thu, 15 May 2025 12:02:44 +0000

If I’m understanding this correctly, if you set off one bomb the explosion travels at a certain speed, but if you put a bunch of bombs in a circle and set them off one at a time, the very last explosion will be going a lot faster than the first one?

New comment by philipodonnell in "Evolving OpenAI's Structure"

philipodonnell — Tue, 06 May 2025 18:05:55 +0000

The contributors to the charity get a write off too

New comment by philipodonnell in "Emergent Misalignment: Narrow Finetuning Can Produce Broadly Misaligned LLMs"

philipodonnell — Tue, 06 May 2025 10:49:24 +0000

There’s a trope where the best white hat is a former black hat because they can recognize all the tricks, I wonder if training an LLM to be evil and then fine tuning it to be good will produce more secure code than the opposite?

New comment by philipodonnell in "The future of AI is Ruby on Rails"

philipodonnell — Sat, 22 Mar 2025 11:07:48 +0000

FWIW I’ve been doing a lot of work with text to SQL and in that space verbosity in naming tables and columns matters a lot because it adds additional context about what data is in the table and how it can be used. Think “subs.id” versus “subscriptions.stripe_customer_id”.

New comment by philipodonnell in "Show HN: OpenTimes – Free travel times between U.S. Census geographies"

philipodonnell — Tue, 18 Mar 2025 00:54:55 +0000

Very cool! What did you use to make the ER diagram?

New comment by philipodonnell in "Brother accused of locking down third-party printer ink cartridges"

philipodonnell — Wed, 05 Mar 2025 04:23:48 +0000

Hi. Maybe anecdotal, Brother MDC-J480DW, had it about 3 years, always bought third party ink, two weeks ago I had to replace the color ones and it started saying there was no ink even though ink was clearly visible, it failed on two different colors from two different sources, and the three different black cartridges, then bought legit from Walmart and worked perfectly. I can’t speak for everyone’s experience, but mine was definitely changed recently to always say third party ink was empty, and I’ll junk it once this ink runs out.

New comment by philipodonnell in "Leadership Power Tools: SQL and Statistics"

philipodonnell — Thu, 19 Dec 2024 13:15:03 +0000

I’ve been working on some tooling to create better views of analytics based on the idea that people don’t like to write joins so why not create logical views that do all possible joins. Appreciate any feedback. https://github.com/eloquentanalytics/pyeloquent

New comment by philipodonnell in "Leadership Power Tools: SQL and Statistics"

philipodonnell — Wed, 18 Dec 2024 17:50:01 +0000

I think a lot of times this is not about skill sets but more that data engineers don’t build datasets with UX in mind. The examples in this piece are not what show up when a leader browses a real database with hundreds of tables stuffed with abbreviations and numeric/short codes. If you want your leaders to use your data, you have to design your data to be used by leaders, not teach them SQL and statistics.

New comment by philipodonnell in "SpiceNice – An Open Source Spice Database"

philipodonnell — Tue, 17 Dec 2024 19:13:05 +0000

I often wonder if you can create databases like this using the data in the training datasets of LLMs. Generate the list of spices by asking for categories, countries of origin, etc and then asking about a list of properties for each. You could use these kinds of Wikipedia lists as a validation mechanic.