Hacker News: JoshPurtell

New comment by JoshPurtell in "Talkie: a 13B vintage language model from 1930"

JoshPurtell — Wed, 29 Apr 2026 14:28:37 +0000

There could be a leak from post-training but not pre-training

New comment by JoshPurtell in "Google releases Gemma 4 open models"

JoshPurtell — Thu, 02 Apr 2026 22:06:54 +0000

gpt oss 20b is not dense

New comment by JoshPurtell in "Astral to Join OpenAI"

JoshPurtell — Thu, 19 Mar 2026 16:39:33 +0000

Codex is not far behind Claude Code

New comment by JoshPurtell in "Astral to Join OpenAI"

JoshPurtell — Thu, 19 Mar 2026 15:58:39 +0000

You most certainly should not have stuck with Conda

New comment by JoshPurtell in "Show HN: BVisor – An Embedded Bash Sandbox, 2ms Boot, Written in Zig"

JoshPurtell — Mon, 23 Feb 2026 19:14:38 +0000

Have been testing this in dev and really like the performance so far

New comment by JoshPurtell in "Show HN: Horizons – OSS agent execution engine"

JoshPurtell — Wed, 11 Feb 2026 14:18:35 +0000

I concede that it is not precisely OSS. But if I tell someone that it is source-available, they will expect some kind of license restriction for any use. If I tell someone OSS, they will expect mostly what the Sentry license entails, unless they are a competitor, in which case I really don't care what they think.

I wish there were a popular term that conveys exactly how Sentry license works. But, there isn't - so I think it's fair to say open source, maybe as a general term. I'll change it from OSS to open source

Specification Driven Development

JoshPurtell — Sun, 08 Feb 2026 18:18:06 +0000

Article URL: https://www.joshuapurtell.com/posts/spec_eng/

Comments URL: https://news.ycombinator.com/item?id=46936954

Points: 3

# Comments: 0

New comment by JoshPurtell in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"

JoshPurtell — Sat, 07 Feb 2026 07:24:28 +0000

What compile times do you work with? I use bazel and it still hurts

New comment by JoshPurtell in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"

JoshPurtell — Sat, 07 Feb 2026 07:04:34 +0000

Billionaires and corporations can hire teams of people to work for them full-time. You, likely, can hire one or two (or zero!). Not to make it personal.

These inequalities already exist

New comment by JoshPurtell in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"

JoshPurtell — Sat, 07 Feb 2026 04:33:13 +0000

I do both and compile times are very unfriendly to AI!

New comment by JoshPurtell in "Show HN: Horizons – OSS agent execution engine"

JoshPurtell — Sat, 07 Feb 2026 04:26:58 +0000

Why, because of the Sentry license?

New comment by JoshPurtell in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"

JoshPurtell — Sat, 07 Feb 2026 04:26:25 +0000

Every AI advancement liberates real humans from drudgery and allows them to create what they want more easily.

The invention of the digital calculator turned human calculators into accountants, and that's great! We're contributing to the same process now

New comment by JoshPurtell in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"

JoshPurtell — Sat, 07 Feb 2026 01:02:02 +0000

rlm-rs: https://crates.io/crates/rlm-rs src: https://github.com/synth-laboratories/Horizons

New comment by JoshPurtell in "Monty: A minimal, secure Python interpreter written in Rust for use by AI"

JoshPurtell — Sat, 07 Feb 2026 01:01:53 +0000

Monty is the missing link that's made me ship my rust-based RLM implementation - and I'm certain it'll come in handy in plenty of other contexts.

Just beware of panics!

New comment by JoshPurtell in "Show HN: Horizons – OSS agent execution engine"

JoshPurtell — Fri, 06 Feb 2026 01:26:08 +0000

Just like codex or opencode provide strong oss implementations of the core agent loop, our ambition (not achieved! hoping this is a solid start) is to provide a solid oss implementation of the context updating loop, memory, basic database + a backend sync layer. And evals + continual learning + gepa optimization.

Just like everyone can write their own agent, yet many opt for codex/claude code sdk/opencode, we think that at some point in our journey, many will also opt for standard implementations of these patterns, for projects big or small.

Realistically, though, the case for a standardized environment grows a lot stronger when you have multi-agent, permissioned actions, and generally just a lot more state than what you can get away with using only opencode + some glue. Insofar as big teams have ambitious products, they might be more likely to try it

Show HN: Horizons – OSS agent execution engine

JoshPurtell — Fri, 06 Feb 2026 00:58:31 +0000

I'm Josh, founder of Synth. We've been working on coding agent optimization with method like GEPA and MIPRO (the latter of which, I helped to originally develop), agent evaluation via methods like RLMs, and large scale deployment for training and inference. We've also worked on patterns for memory, processing live context, and managing agent actions, combining it all in a single stack called Horizons. With the release of OpenAI's Frontier and the consumer excitement around OpenClaw, we think the timing is right to release a v0.

It integrates with our sdk for evaluation and optimization but also comes batteries-included with self-hosted implementations. We think Horizons will make building agent-based products a lot easier and help builders focus on their proprietary data, context, and algorithms

Some notes:

- you can configure claude code, codex, opencode to run in the engine. on-demand or on a cron

- we're striving to make it simple to integrate with existing backends via a 2-way event driven interface, but I'm 99.9% sure it'll change as there are a ton of unknown unknowns

- support for mcp, and we are building with authentication (rbac) in mind, although it's a long-journey

- all self-host able via docker

A very simplistic way to think about it - an OSS take on Frontier, or maybe OpenClaw for prod

Comments URL: https://news.ycombinator.com/item?id=46907651

Points: 39

# Comments: 8

New comment by JoshPurtell in "It's 2026, Just Use Postgres"

JoshPurtell — Fri, 06 Feb 2026 00:38:45 +0000

It's 2026, just use Planetscale Postgres

New comment by JoshPurtell in "Sam Altman responds to Anthropic's "Ads are coming to AI. But not to Claude" ads"

JoshPurtell — Thu, 05 Feb 2026 02:05:39 +0000

Completely absent of substance

New comment by JoshPurtell in "Claude is a space to think"

JoshPurtell — Wed, 04 Feb 2026 20:10:50 +0000

From Sama "More Texans use ChatGPT for free than total people use Claude in the US, so we have a differently-shaped problem than they do"

Facts don't care about your feelings

New comment by JoshPurtell in "Claude is a space to think"

JoshPurtell — Wed, 04 Feb 2026 17:49:31 +0000

Important to note Anthropic has next to no consumer usage