Clanker Wrangler. Fractional SWE/SA.
- Tweets 1,015
- Following 293
- Followers 88
- Likes 10,118
"Cost per task" is such a terrible metric/benchmark if your use case is non-automated coding tasks. What a lower cost-per-task metric for an LLM means in practice, for coding, means writing unintelligible code, which while technically "correct" is barely readable slop to humans
At its default effort setting, Opus 5.5 delivers frontier results for a fraction of the cost per task, often beating other models running at their highest settings.
It also generates output more than 30% faster than Opus 5.
1
273
> We’re also providing subscription users a rate limit reset, which you can save and use whenever you choose.
H'mmm. Where have I seen this before? 🤔🤔
One more thing: we’re increasing five-hour usage limits on Pro, Max, and Team plans. We’re also providing subscription users a rate limit reset, which you can save and use whenever you choose.
1
86
At the risk of anthropomorphizing, do you think LLMs ever get excited when they get to read well-known closed-source codebases? Like if someone was to start Codex in the SC: Brood War repo would GPT's first reasoning trace be like "fuck yeah"?
59
How existing Pro subscribers be feeling right now
To make sure our current users have an incredible experience and continued access to Astra, we are going to pause subscriptions to our $200 Pro plan. These put the most strain on our systems and we wanted to take the smallest step that allows us to continue giving the broadest access possible. All other plans and the api remain available.
There is no impact to existing accounts and we are working on adding more capacity as fast as we can. Thanks!
38
The pursuit of excellence does not need justification
Mind boggling to me that I can make a thing faster and there's always people that ask "but why?" What kind of mentality is that? The pursuit of excellence does not need justification. Also, I find in so many cases, we can't know the impact of an improvement until we do it.
For example, one I've talked about before: Ghostty's high IO throughput has enabled terminal program (emulator and TUI) fuzzing at a speed thats incomparably fast to prior solutions. This has resulted in upstream patches to resolve issues in popular projects like btop, tmux, and more.
Speed enabled that anecdotally example that lifted the tides of adjacent communities that don't rely on Ghostty technology at all. I didn't predict this.
Make things better because they can be better and let the results naturally play out.
2
188
Wait until employers figure out that replacing the Unlimited Token perk with Unlimited Monster Ultra Zero is a far better return on investment.
1
2
161
