Eric Hauser

CTO at Cadence -

[Eric Hauser @ewhauser]

@thsottiaux @ah20im Been working on a Go port in case it's useful to anyone: https://t.co/RiOqbxerCZ

[Eric Hauser @ewhauser]

@Micks2B @coachravindrak I'm sure it just comes down to the math on the probabilities of the hit rate

[Eric Hauser @ewhauser]

@RhysSullivan @zeeg That’s exactly how it works? I just type “submit a PR” and it links

[Eric Hauser @ewhauser]

@WadeWegner @dkundel I’m a long time tmux user; was the alpha for coding agents up until a few months ago. The app is the way

[Eric Hauser @ewhauser]

@jxnlco @mweinbach 1) UI/UX significantly better (even dashboard viz) 2) Non-technical business writing/analysis. Give some data to both models and ask them to use the Google doc skill to write an operating plan. Opus much stronger. I’ve thought GPT>Opus for coding since 5.2, but still weaker here

[Eric Hauser @ewhauser]

@karrisaarinen @linear Activity vs. guide vs diff should be sticky when you go from one PR to the next

[Eric Hauser @ewhauser]

@karrisaarinen @linear Give this a try. Biggest complaint relative to GitHub's UI is that the screen is too busy. When I open the review diff, I have 3 panels to look at - 2 of them which I don't really care about (your nav + list of PRs to review). If I do Guide mode, I have 4 panels.

[Eric Hauser @ewhauser]

We have to hit a 40B ARR run rate to have product-market fit now?!?!

[Simon Willison @simonw]

Given the recent burst of activity around enterprise pricing and contracts, I think April 2026 was the month when both OpenAI and Anthropic found product-market fit https://t.co/0hgMfu9Khx

[Eric Hauser @ewhauser]

@brandur @ericwithcoffee Believe xhigh uses 30% more tokens on 5.5; while medium uses less tokens than 5.4

[Eric Hauser @ewhauser]

@carllerche Tokens, turns used to accomplish the same task

[Eric Hauser @ewhauser]

@carllerche Evals?

[Eric Hauser @ewhauser]

@carllerche 2) writing bugs related to it. I was blown away the first time I had an agent write Rusr code because the reduced turns and cruft related to no nil was noticeable

[Eric Hauser @ewhauser]

@carllerche I’ll caveat this by saying that I’ve probably written as much AI generated Go code as anyone out there. Codex/Claide are really, really good at Go. The one thing that’s incredibly annoying is the extra cycles it spends 1) writing Go code I wouldn’t write guarding for nil

[Eric Hauser @ewhauser]

@brandur Congrats!

[Eric Hauser @ewhauser]

@chaliy I'm probably not the right person to own a distribution of it to be honest. Hoping that sharing it might encourage some exploration by people who know Postgres better than me

[Eric Hauser @ewhauser]

Forked an experiment for an ephemeral Postgres for faster unit testing (https://t.co/z40XEC4b1c). 2.5x faster with no changes; 3.3x with minor schema setup changes. Day's worth of background work; imagine someone who knows PG internals could get a much larger improvement

[Eric Hauser @ewhauser]

@_lopopolo @steipete What's the limitation in review mode where it only returns 1-2 things each turn and then I have to keep running it until it runs out of things to find? Has to better a better way here. Run "/goal Keep reviewing until you run out issues to find"?

[Eric Hauser @ewhauser]

@cramforce zizmor flags cache poisoning and pull_request_target. Not using it on all your repos is just lazy

[Eric Hauser @ewhauser]

@valigo They ported this in a week. Once the test suite passes, then you start to refactor. You think if they spent the next 4 weeks refactoring then it wouldn't be maintainable?