rgbrgb

randomly stating who you are

it's not random at all. that's literally what the resume is supposed to be and what the hiring manager wants to know! This is a real human hiring manager sharing candid feedback on his acceptance criteria. So there's at least one company where this is pretty sound advice.

your point about the dumb filters is plausible but at some point a human is going to read it and try to decide if they want to work with you. If all they have is some AI output, it's going to be an easy no.

in my experience models will answer introspective questions decisively but can't actually introspect. this is pretty similar to humans (e.g. ford's faster horses quote).

with AI stuff you can actually run real tests though.

looks cool. what is latency like? I haven't used qmd before and it looks like it runs 3 local models.

Why do you think you were audited?

A version of this I've been enjoying is mostly solo dev but with a biz-guy partner. I mostly just build software but have a partner who will go find out how people are using it, what they want, handle inbound, and be there to chat about ideas even if we're not getting into the technical weeds.

i guess not. you're right, this is not cool!

~was truly surprised and delighted by this today. claude's recs are usually pretty good. imo as a product engineer this is a good default and all the cranky experts in here can turn it off.~

edit: didn't read closely enough to realize this can't be disabled / think about the perverse incentives. seems bad actually

This is cool. I was skeptical of MCP's until I made one recently. They're essentially the exact same as 1) giving your agent a CLI tool or REST API and 2) pointing it there in an AGENT.md/CLAUDE.md. Agents are great at using built-for-human CLI tools and IMO they don't need anything purpose-built for agents. The key difference, which ends up being a usability win for non-technical users, is that the MCP bundles 1 and 2 - harnesses inject the MCP tool descriptions on every session after install. Of course, that's also why you need to be careful about context bloat when using/building them

Notably it has 0 wins.

congrats on the launch! site and docs look great.

can you host this yourself or do you need to use helix-cloud? the chat thing on the side seems to push me to helix-cloud but it looks like that starts at like $600/mo which is above my experimentation budget.

looking for a db for an agent memory application and i'd probably start with something that's just self-hosted / freeish. postgres is working ok but I want to start ingesting server and chat logs.

very cool. session replays are so crucial for understanding new features qualitatively, especially before you have enough users for useful quantitative metrics.

ballpark, how much does this cost to run?

fwiw my experience building a small tech talent agency / recruiting shop disagrees with this. Cold application pipelines are overwhelmed by gen AI applications and many of the (very qualified) candidates we place report getting totally ghosted on all cold applications - even when we’re able to get them several interviews a week with companies in our network.

Seems like companies still value a curated pipeline. 15-20% of first year salary (numbers we see these days) appears to be worth saving the company time interviewing unscreened candidates. Recruiting can be a real time suck and a bad hire can be catastrophic.

Congrats on the launch!

Agents can now get an email inbox by themselves. (This also means a lot of email nobody wants to read gets processed by AI instead of your inbox being cluttered with spam and slop)

Can you explain this? I would think it means the exact opposite.

i love this because it seems like you've turned vibecoding up to 11 unleashing the non-technicals in your org to ship vibecode slop straight to prod. it's an idea so obviously terrible to most engineers that maybe it's actually really really smart. much bolder than yet another AI-driven dashboarding tool or smart notebook.

to address the elephant in the room... how do you think about technical debt incurred by users who likely do not understand the underlying data models, consider auth, etc?

I built a toy BS with very dumb agents in school in 2012 or so. Multi-agent systems were kind of fringe and retro. It's nuts that modern agents look about the same (basically an OODA loop) but replacing the hand-coded "orient" and "decide" with an LLM is so much easier (for me, a frontier model user) and 100x more capable.

The use-case for multi-agent systems are intuitive from a human perspective (one person can't be an expert in everything) but a little less so with LLM's since, so far, it seems like we use a single frontier model that's pretty good at everything. That said, even a single person has little breakthroughs with different context / sleep / "mind space" so I'd guess there's some useful way to scale that idea usefully with multi-agent systems. I think a lot of these old AI ideas are rich for exploring with LLMs.

what harness do you use with all of these?

I’ll share more details about where the Ghostty project will be moving to in the coming months. We have a plan but I'm also very much still in discussions with multiple providers (both commercial and FOSS).

what a cliff hanger!

As someone with similar warm feelings for GitHub, it's kind of sad to see the fragmentation but I have similar frustrations with the recent outages. Perhaps it's time to explore the idea of unbundling the social/discovery layer from the code hosting/dev tool so we can live between the myriad git/jj hosts but still do "social coding" together.

I'd guess the same has always been true for READMEs / human dev docs. Of course it doesn't transfer directly but still feels incredible to be in an age where we can measure such (previously) theoretical things with synthetic programmers.

It would be really cool to do a causality investigation to determine which one of these boosts it so much / quantify how much each matters. Who knows, they may all interact in a sum-is-greater-than-parts way that only improves the score when shipped altogether.

what is Tana?

looks great, congrats. quick note, the examples are really cool, but the link in your blogpost is broken.

working link: https://misery.co/shaderpad/docs/getting-started/examples/

to be fair, that's exactly what's at issue. controlling AI implies controlling society as intelligence scales.

impressive. how do you pronounce it?

love the simple website and typography. AI design or you? tasteful and fast animations. nice work and thanks for sharing!

Isn't a standalone Bun binary like 50MB because it has to bundle the runtime? How could this get smaller?

nice, congrats on launch. To get an idea... what's the size of a standalone hello world cli binary?

It seems that the architecture you describe still gives the key to the agent (who could email it to red team or perform nefarious actions with it). The advantage of OP's architecture is that the agent never sees the key and you could inspect the request before proxying it. Is that right or do I misunderstand something?

everyone knows why this purchase was made

you should say what you're talking about because I for one have no idea.

Cool, congrats on shipping. Looks similar to worldmonitor [0][1]. What's the main use-case for this kind of thing? What' the "Watch Floor" you mention?

[0] https://github.com/koala73/worldmonitor

[1] https://www.worldmonitor.app/

FWIW I just tried this to monitor / shepherd a PR while I was on the exercise bike and it was pretty seamless. Way easier than the tailscale/vibetunnel thing I got burnt out on last fall.

I was using the Claude app on my iPhone and claude code on a MacBook pro. PR is merged, still on the bike :)