alright all of you that maintain a cli oauth flow i hope it's obvious to you now doing the whole browser link callback to localhost thing is dumb and annoying af in ssh please implement the code flow that polls - try gh cli login flow to see it

someone connect me with pewdiepie so i can get him a preview of opencode 2.0 which is better for his use case

my goal is to keep kit so busy that "Later" never happens

when ai does something corny (frequent) and you tell it "no that was corny" the next thing it does continues to be corny

i have seen enough proof now that using a coding agent is a deep skill it's confusing because the people you see heavily using them produce horrible results but that's because it's a skill! you can get better and the ceiling seems pretty high - this is very exciting to me

the whole "when a measure becomes a target, it ceases to be a good measure" thing is def real but now people think looking at any metric is pointless the root issue is when your team is motivated incorrectly and would prefer to game a metric instead of learning from it

chat was dead until we started talking about clickhouse of all things

does anyone i know have a connection with someone who works on LetsEncrypt? have a concept i want to run by them

FireWire was such a fire name

one thing i've been enjoying doing is any medium to large size task, i'll ask OpenCode to split it into groups of work we can tackle one at a time then we go through the list one by one often times i can confirm tests and commit after each group so it's like a save point

codex subscription endpoints have had some issues over the past week - you may have noticed some stalling in OpenCode we put in some patches in v1.15.11 that should fix it

a lot of programmers work in the tech a lot more of them work outside of tech tech makes a lot of revenue per employee - if they had to pay 2x per programmer it probably wouldn't matter very different for everyone else worth thinking about in terms of coding agent spend

it is crazy to what extent he refuses to wear sleeves

our next team offsite is soon and everyone is talking about all this gossip they have that they're gonna spill the details on and i don't have anything can you guys tell me some juicy shit

this is the best model i've ever used

there are a lot of reasons to want to run models locally cost is probably not one of them

think back to projects you've worked on in the past it's hard not to imagine they'd have been completed way faster now that we have ai but everything still feels as slow and as difficult as ever

effect is actually bad for agents

every company that works has set up a funnel this funnel is delicate and intricate with many critical pieces working exactly right. it's not an obvious and if it were it would have no value which is why it's very easy for employees to break this funnel

crazy few days for anon accounts

any lack of polish now gets equated to ai slop all fields: software bugs, bad movie, bad video game before the audience would make a judgement about your skills, which was tolerable because you can get better now they make a judgement about your character (lazy/fraud/etc)

had OpenCode run some benchmarks comparing - git cli - libgit2 - gitoxide - isomorphic-git even with process spawning overhead, git cli usually won everything that said i was on linux, overhead on windows probably kills it

ok this was immediately a bad idea

we setup gangprompt.​opencode.​ai (threw it behind cloudflare access for SSO) which is running an opencode server on a fast machine with all our repos cloned now our whole team can pop in there and prompt some stuff and see everything everyone is doing

shhhhhhhhh

at the stage where most of my day is configuring new SAML apps in google workspace

had opencode build a way to declaratively apply a schema to a sqlite db in any state - first pass iterated table by table and tried to mutate db to get it to match - i told it to try an ast, diff, apply method - it did that but the public apis were ugly 1/2

the latest flavor of agents being bad at writing tests is instead of testing a module, they do a dummy re-implementation of it and call that wonder what's making them particularly weak at this

everyone is building things for agents who is building things for asians?

just got inside info that openai is working on a new model

we're going to hit 1M daily active users in the next few weeks the whole way here almost all the thought leaders kept explaining how what we were doing was wrong, bad taste, wouldn't work, etc none of them were curious enough to ask us what they got wrong

so what exactly is the history channel

remember how when we were growing up wall street was the bad guy and everyone hated them and every movie had them as the villain that's tech now

the whole sdk category that stainless was in never made much sense to me it turned what should be a simple run anywhere process and put it behind a cloud service that forced all these awkward workflows we've been building on and sponsoring heyapi for the past year

man i thought they were in openclaw outfits at first i need to get out of the bubble

the bun to rust thing i've had little feeling around it besides "huh that's interesting wonder how it'll go" and i'm 100x more impacted than the avg person but so many people here so worked up over it on both sides of the argument i don't get it

every day i wake up and read a hundred comments telling me im an idiot and doing everything wrong they're never right but there's usually an underlying thing we are doing poorly and once we fix in then there's a new thing and then this repeats till we die i guess

LLM APIs need to return cost information in their response alongside tokens literally everyone is using models[dot]dev data to approximate this - we see so many reqs to its api but this is just sticker pricing, won't reflect discounts, etc so it doens't really work

OpenCode's worktree feature will ship next week out of experimental once we finish one feature that pairs really nicely with it what do you think that feature is?

in OpenCode 1.50.1 you can pin sessions i've been using this with the experimental /warp feature to run each PR i'm working on in its own git worktree and pinning it when i start my day i pickup from what's on this list

branded types for absolute vs relative paths are gonna save my life

wait does gooning not mean coding?

i'm working on some sdk design for v2 what i keep coming back to is not fully understanding one segment of the usecase every infra company is prepping for "millions of agents to run on us" are you working on a product that needs this? tell me more

i'll spend months flirting with a concept and the finally understanding it then it'll be a few more months until i master it enough to articulate it to others and when i do i get the reply "you're just realizing this?"

im not an honest person i squash my commits

i had a good several week run with gpt 5.5 today was completely miserable im so mad rn

our team spends more on AI image gen than coding

something is going wrong with gpt 5.5 caching doesn't look like much on this chart but this it's now using 2.5x as many input tokens as a week ago and dropping

sometimes i get bored and go to a random tech company's website to see how they're pretending to be all about ai now