guybedo

📈 @edgefoundxyz trading alerts + backtests
🔧 ai powered productivity

[guybedo @guybedo]

sneak peek at @edgefoundxyz new desktop app.
Building a setup on $BTC.
high => low => sweep the low => reclaim ema 10

[guybedo @guybedo]

tbh when they reset limits it's not interesting and you can actually lose your token budget because they also push back the next reset date. Say you have managed to still have 30% left for the next day, they reset, boom you lost your 30%.
When Anthropic resets, the next reset date isn't pushed back, you actually get a new 100% to spend until your reset date. this is real reset

[guybedo @guybedo]

Claude 529 529 529

[guybedo @guybedo]

LOL Claude sets his timer and thinks he's sleeping for 5min when in fact he launches the timer in the background and just comes back immediately: "it's been going for 50 mins...55 mins..."

[guybedo @guybedo]

it comes from the right place but resetting usage + moving the reset date isn't helping. You shouldn't update the expected reset date.
What you're doing here is just getting us into a new cycle: we have 100% and it resets in 7 days.
When Anthropic resets the counters, they keep the same reset date, that means we actually have new credits to use until the expected reset date. 100% and 3 days to use. That's actually interesting.

[guybedo @guybedo]

@iruletheworldmo if they really solved frontend, Claude is done.
Frontend work is the only reason i'm still keeping a Claude sub right now

[guybedo @guybedo]

@elliotarledge Minimax 3

[guybedo @guybedo]

@TrustlessState in this sci fi novel, is ETH actually successful ?
or is it more science than fiction ?

[Ibragim @ibragim_bad]

🚨 SWE-rebench big March-May update!

SWE-rebench is a live benchmark with fresh SWE tasks (issue+PR) from GitHub.

updates:
> we collected more fresh and complex tasks
> we ran 110 tasks × 5 for each model / scaffold
> the differences between models and scaffolds are now easier to distinguish
> we will update the task set every two months, with model updates in between

insights:
> GPT-5.5 xhigh takes #1 with 62.7% resolved and 70.0% pass@5
> Cursor with Composer 2.5 is very cheap and strong: around 8× cheaper than Claude Code and Codex, and scores higher than open-weight models! @leerob

Model updates will come in 1–2 weeks. Please send requests for models you want us to run!

🏆 Full leaderboard (check for price / tokens per problem, pass@5, scaffold params, etc):
https://t.co/9jL4lt4UGl

👾 Join our Discord:
https://t.co/cyWgceqqDa

[guybedo @guybedo]

@Polynesiela1ere petition en ligne: https://t.co/VYlRz4hK5K

[guybedo @guybedo]

@shengzheyao https://t.co/zMNMsIoYDL

[guybedo @guybedo]

@_mohansolo I'd love to try Antigravity Cli, but i can't, although i'm a Google AI subscriber.
Google still doesn't know French Polynesia is in FRANCE, why are we still being gated ?
https://t.co/g7y9v9uYbs

[guybedo @guybedo]

@antigravity a nice feature would be to actually be allowed to try it out: https://t.co/Zs3oHx0vaj

[guybedo @guybedo]

@_mohansolo I'd love to try Antigravity Cli, but i can't, although i'm a Google AI subscriber.
Google still doesn't know French Polynesia is in FRANCE, why are we still being gated ?
https://t.co/g7y9v9uYbs

[guybedo @guybedo]

@rseroter @antigravity @iRomin https://t.co/zMNMsIoYDL

[guybedo @guybedo]

@_mohansolo I'd love to try Antigravity Cli, but i can't, although i'm a Google AI subscriber.
Google still doesn't know French Polynesia is in FRANCE, why are we still being gated ?
https://t.co/g7y9v9uYbs

[guybedo @guybedo]

@serenaa_ge it'd be great to run benchmarks for other effort levels, at least for gpt and claude. For example: gpt 5.5 high and medium.

[guybedo @guybedo]

@skirano ferrari luce vs nissan leaf

[guybedo @guybedo]

@zerohedge how do you say your AI division has failed without saying it: just rent all you compute capacity to frontier labs

[guybedo @guybedo]

@DavidOndrej1 nice, do you have a cheat sheet reco or something for building layouts like this ?

[guybedo @guybedo]

i just started using tailscale as i had to move for the week.
It's been super easy to setup and it just works.

[🚨 AI News | TestingCatalog @testingcatalog]

ANTHROPIC 🔥: Mythos 1, "claude-mythos-1-preview", is being prepared for a release on Claude Code and Claude Security.

The model became visible for a short amount of time on Claude; besides that, new strings mentioning Mythos have been added.

> Access to the Claude Mythos model in Claude Code and Claude Security.

It still doesn't mean the general public will have access to this exact model, according to Anthropic's earlier communication.

More below 👇

[guybedo @guybedo]

@kevinhou22 https://t.co/zMNMsIoYDL

[guybedo @guybedo]

@_mohansolo I'd love to try Antigravity Cli, but i can't, although i'm a Google AI subscriber.
Google still doesn't know French Polynesia is in FRANCE, why are we still being gated ?
https://t.co/g7y9v9uYbs

[SpaceX @SpaceX]

Liftoff of Starship!