Pete Hunt 🚁

@headinthebox clado now partnering with clodo

"... I think it’s unrealistic for AI to handle your entire recruiting workflow ...” November 2025 [0] "... Clado is no longer being developed and will be shutting down in 2 months. ..." March 2026 [1] If you are building an AI-powered product, you have to believe in it 200%.

@kirkmorales My experience as well

@floydophone Couldn’t get it to actually do anything without hanging or failing every tool attempt

Was anyone else underwhelmed by Claude cowork?

@podviaznikov Just very buggy

@floydophone I think most people who used claude code directly underwhelmed by cowork. but for people who didn’t experience claude code cowork seems like an interesting and useful thing?

@iwilsonq Lots of potential and very pleasant design, but very buggy and unreliable

@floydophone its definitely not as smart as the CLI and it hangs often. Somehow its also harder to setup a custom MCP with it as well

@c_pick yeah, upsetting is exactly the right word for it haha

@floydophone very upsetting visual design taste though

polsia is definitely the best ai startup name so far

@dflieb blame lies equally with product/eng leadership that doesn't know how to handle these conversations

I’m bullish on Google for many reasons. One simple example is this feature that we wanted to ship 10 years ago but was constantly blocked by lawyers. Google is maybe finally in wartime mode.

@swyxio Earned it

@travismarceau 😐

@floydophone MDS could do for a makeover. Y'all should try one.

Remember sandboxes?

@TacticalMinivan soon we will remember "agent harnesses"

@floydophone Pepperidge farm remembers Pepperidge farm also remembers “prompt engineers”

@dexhorthy we'll need rehearsals and wargames haha

Here’s what’s gonna happen: - you replace your code review with feedback loops (sentry, datadog, support tickets, etc) - you stop reading the code - software factory fixes everything - one day something breaks at 3am, agent can’t fix it - nobody’s read the code in 3 months - you have 3 weeks of downtime trying to re-onboard and fix it - you lose significant % of your contracts and users - your company is now dead

@Noahpinion yeah but this one is particularly egregious

Everyone in the tech industry talks this way now

200ktok ought to be enough for anybody

This is a monumental release: Concurrent Writes are finally here. When we started Turso more than a year ago, we asked a large number of people what is the thing that SQLite lacked but they wanted to see the most. The result was overwhelming: Concurrent Writes. It is not an easy feature to build: the whole database needs to be able to support MVCC (Multi-Version Concurrency Control). But it possible and doable because we have a full rewrite from a blank slate, and a great and reliable foundation of deterministic testing with both @AntithesisHQ and our own simulator. MVCC is now no longer experimental and will enter a short beta period (which we do for all features) before we call it GA. But that's not the only AMAZING thing in this release: SQLite is known to be a very permissive database. Types are suggestions. Turso now not only support STRICT tables, but comes with a type system including the ability to create your own types with the CREATE TYPE statement. Turso is SQLite reimagined for the age of AI. And it is hard to think of something more important and more overwhelmingly victorious than types. For the full changelog and goodies, see the post below!

@nilslice @BraydenWilmoth Maybe it is but it’s 10x less than what came before. Agree that 90% of this is feels

react is probably the cause of more subtle bugs in any system than any other piece of software, so idk if that’s really a good point to make but i can appreciate the analogy idk, just feels like baby JavaScript company is triggered but they’ve been slopping all over the place for months. can dish it but can’t take it is amateur mode.

the "slop fork"... faster & smaller.

@BraydenWilmoth @nilslice It’s brilliant marketing, I’ll give you that. Everyone loves a line chart. And it’s not hard to be happy for new things that solve problems for other people. Like why would you say that?

@floydophone @nilslice It’s hard to be happy for new things that solve problems for other people :) “untested” yet built off tests. Still early and experimental and we’re excited about what’s possible in this new age of AI. Hopefully you can be excited for other people at least!

@drewhamlett @BraydenWilmoth vite can be good and this stunt can still be lame!

@floydophone @BraydenWilmoth Next wouldn't be bad if it used Vite. Problem solved.