Ben McHone

Tinkerer, tech enthusiast, Software Engineer. All of my tweets and opinions are my own.

[Ben McHone @mchonedev]

@thdxr Pfft that's nothing.. Wake me up when you work 8 days per day

[Ben McHone @mchonedev]

@sudo_overflow You couldn't even say 1900's? 😂 Man you just made me feel ancient

[Ben McHone @mchonedev]

The `/prototype` skill from @mattpocockuk is sweet! I started trying to imagine a few different routes that a UI tweak could take but the interactive prototype let me have a great convo with my team on tradeoffs and UX!

[Ben McHone @mchonedev]

@mattpocockuk How do you foresee teams getting comfortable with taking bigger swings using grill with docs/to prd/to issues?

[Ben McHone @mchonedev]

@sydneyrunkle @Hacubu Deep agents just keeps getting better! Great work 👏

[Ben McHone @mchonedev]

@TracketPacer So you're saying I'm basically on my death bed? Got it 😂

[Ben McHone @mchonedev]

@MaximeRivest Now the PR mentioned absolutely allows one to build this, so I think we're on the right track 😁

[Ben McHone @mchonedev]

@MaximeRivest I think that sounds like a nice place to be. I wonder if we could go even simpler. A `CallbackLM` or similar that lets you delegate to anything. Then DSPy is responsible for everything except for inference. Users can keep any existing libraries and incrementally adopt DSPy.

[Ben McHone @mchonedev]

@TracketPacer Understood. Thanks anyways!

[Ben McHone @mchonedev]

@sethtjf I was actually looking at this recently to handle rollout of enterprise skills. Turns out fastmcp has something kind of like this built in.

https://t.co/FaeDfpocoK

[Ben McHone @mchonedev]

@sudo_overflow Not to mention mini PCs can be had for CHEAP on eBay or Facebook marketplace. I already had a home server, so a new vm was like 5 minutes to setup

[Ben McHone @mchonedev]

@ryanvogel @MegaBasedChad Haven't you heard? It should be written in rust!

[Ben McHone @mchonedev]

@sudo_overflow @NousResearch Mine runs in it's own vm locally for now and I'm using openrouter at the moment. Planning to swap in either codex or open code go to better support my own cost planning

My goal is as little friction without undue risk of over exposure to sensitive personal capabilities

[Harrison Chase @hwchase17]

switching model providers is easy

switching harnesses is less so

model providers want to lock you in via harness

we need open harnesses!

[Ben McHone @mchonedev]

@samuelcolvin @pydantic Being able to change a model string and be on my way without worrying about endpoints is agnosticism.

If you're talking more about prompt management, then I would defer to evals + optimization like GEPA

[Ben McHone @mchonedev]

@samuelcolvin @pydantic You asked how people manage it, so I shared how I do it 😄

Local proxies exist too (See LiteLLM and similar)

The advantages of a gateway can be fallback, caching, etc but it can ALSO be a solution to model agnosticism.

I don't want to be forced to use a specific library.