sean gil

dad. dev. army veteran 🇰🇷🇺🇸
former military intelligence and private/corporate investigator
senior eng @ hammer media

[sean gil @doughydev]

I had 5 agent sessions on one repo at work (2 Claude Code, 2 OpenCode, 1 Pi) and they kept clobbering each other's changes.

Worktrees would've split work that belonged together. I just wanted the sessions to be aware of each other.

So I built that. Open sourced it ⬇️

[sean gil @doughydev]

Repo: https://t.co/ICl9dDmtrw
Docs: https://t.co/3hTjTEOlcz

Install is one line:
curl -fsSL https://t.co/imM7PDB5GH | sh

MIT licensed. Would love feedback from anyone running parallel agents.

[dax @thdxr]

at this point i think morality should be a private matter between you and your family

every time i see it made part of a public identity (like a company's mission) it corrupts everyone involved and they justify increasingly worse behavior

[sean gil @doughydev]

@jonathan_wilke Yeah they are a bit annoying. I built a small local cli that allows me to mostly avoid worktrees. Agents claim areas and warn each other before editing

[Mitchell Hashimoto @mitchellh]

Fable is a good model. As with all new models, it is simultaneously excellent and entirely unremarkable (relative to other models). It is slow and expensive, and the "loops are all you need" discourse they are pushing is obvious in the context of someone using Fable-class models

What I've found so far is that for broad scope design (code architecture) tasks, Fable is unremarkable. Or, not better enough to justify its cost and speed.

But in highly targeted goal-oriented loops, it is another beast entirely. It is very slow but produces very good results.

I let it churn on optimizing a SwiftUI-layout resolver in Go I wrote and it was able to bring it down to an order of magnitude I could not reach myself (micro => nanosecond scale). But it took 2 hours and $40 to do it and I had to claw back some changes it overfit to Apple Silicon. Still, very worth it.

In comparison, for "implement this feature/change" iterative work, I ran head-to-head Fable vs GPT5.5 vs. GLM-5.1. They all produced equally acceptable final results, but GPT5/GLM did it in a couple minutes and Fable was churning away for 40 minutes. And GLM cost me less than a dollar, GPT5.5 ~$1.50, and Fable cost $9.

You can see that in this context, interactively working with an agent is nonsense. Its too slow. You need to write loops to keep the agent working and you probably want to highly parallelize the work being done. As with all things, I think a balance makes sense...

My sense is that I'd reserve Fable for targeted, surgical analysis and work. Not for daily driving everyday tasks.

I'm going to keep spending a shitload of money (relatively) and maining Fable for the rest of the week to continue to judge, will report if anything changes. I'll continue to head-to-head as well.

[Low Level @LowLevelTweets]

If the vibe coders could read they’d be very upset

[sean gil @doughydev]

@bridgemindai sorry but skill issue. this seemingly is only true strictly for vibe-coding-only developers

[sean gil @doughydev]

@rekram11 👀👀

[sean gil @doughydev]

@GithubProjects go fix yourself

[dax @thdxr]

we've seen reports of this for a while now - almost a year

they investigated and concluded they're very convincing hallucinations

super weird because you get very specific, very random responses

[Joe Rogan @joerogan]

Episode #2509 @sircalebhammer
https://t.co/l3cMtEJbBL

Caleb is a very smart and entertaining guy giving legit financial advice to a generation who desperately needs it.
Episode is out now on @spotify and everywhere else

[sean gil @doughydev]

@orcdev codex and claude pro (through work), opencode zen (gna get go when my credits for zen run out)

[sean gil @doughydev]

@Polymarket this the random bullshit I like to see on X

[Caleb Hammer @sircalebhammer]

Rogan episode is live, check it out!

[sean gil @doughydev]

fun and meme-y but my mind is blown.
makes me think about the future of software. exciting times!
https://t.co/2nTmculAh1

[sean gil @doughydev]

@kitlangton @opencode fire 🔥

[sean gil @doughydev]

@bridgebench which plan? Im on the pro plan and not even close to my weekly usage and I use it heavily

[sean gil @doughydev]

anthropic's shitty ToS means I use claude code for my company's inference, but my daily driver is still @opencode with Codex/Zen.

to keep agents from clobbering the same repo, I built Weaver: local task/claim/check/notes between sessions.

https://t.co/9gChzVk22y

[John Loeber 🎢 @johnloeber]

Notes on 100+ Recent Technical Interviews

I interview a ton of engineers. Recruiting is the single most important technical CEO activity. Here are a bunch of impressions

1. There is a severe ZIRP engineering overhang that is currently washing out. They're getting laid off, managed out, etc. after having been massively overhired around 2020-2022. This is worst for Tier-2 big tech (think PayPal, Bill, etc.) but also FAANGs. These are overwhelmingly bad engineers.

2. This flood of unqualified but good-on-paper candidates makes this the hardest SF hiring market I have ever seen, due to the amount of nominally strong-looking candidates that you need to grind through.

3. I am highly skeptical of "AI as a cause for engineering layoffs". I think this is a large-scale polite fiction -- the companies don't want to admit they overhired, the engineers don't want to admit they are bad at their jobs. Everyone's blaming AI when it's really just the market rectifying itself.

4. Many of these engineers appear never to have had a real engineering function at their corporations. They're sitting in meetings, "making decisions about technology" but are unable to write software. I leave many interviews baffled by what exactly they were doing for so many years, let alone what their manager was doing.

5. I have interviewed some engineers from FAANG companies so shockingly nontechnical that I am forced to conclude that there is either (1) a lot of resume fraud going on or (2) that there are kickback grifts within those organizations -- people hiring their cousins and splitting the pay, that kind of thing. I have no other explanation.

6. There's a fun side-effect where after interviewing 20+ people from certain small but public companies, I actually feel like I am gaining a short sellers' advantage: there are financial technology companies out there that, knowing what I now know, I would never deposit a single dollar into.

8. Based on this "exhaust" data, and extrapolating a little bit, maybe aggressively so: I think folks like @pmarca are basically right when they say that ~every tech company is overstaffed by a factor of 2-4x. Whatever the reason -- staffing ahead of need, monopolizing certain engineer types (Google-style), headcount-driven promotion incentives, the reality is that a lot of these companies are not being run for the shareholders. The aggregate SBC expense is insane, and I expect this is going to get rectified eventually.

I'm sure that AI will play a role in rectifying this -- but I fear that people are going to blame AI for taking people's jobs when the reality is that the jobs were already long-gone, possibly always useless, but the highly-paid butts-in-seats remained. People will be mad at AI for taking away their lucrative sinecures. Maybe that's the same effect from a public policy perspective, but it feels different morally.