Sabitlenmiş Tweet
Alex
779 posts
Alex
@Alex_FF
Producer for @forwardfuture and the @matthewberman channel
Katılım Mart 2025
82 Takip Edilen330 Takipçiler
Turn on voice mode. Put the phone face down on your desk. Instruct it to stay quiet until you invoke it directly.
Do your work like normal, but then
Use it as your Google replacement or verbal brainstorm partner that you can access without switching windows
Forward Future Brian@ForwardEditor
New ChatGPT Voice one shot me today imagine there's a friendly customer service agent who knows everything about everything you can call any moment and there's no wait very much a "feels future" moment
English
My favorite loop right now is optimizing my project until it reaches a 90% score on the benchmark I created.
English
What are other examples in tech of building the best version of something but it costing too much to serve/sell?
Matthew Berman@MatthewBerman
If Anthropic pulls Fable from the Claude subscription, they will be ceding substantial coding mindshare to OpenAI. Will be a big mistake.
English
Alex retweetledi
@MatthewBerman @morganlinton Is it cuz you got that fancy keyboard that’s fun to type on
English
@morganlinton I keep wanting to do voice prompting but I keep falling back to typing…
English
@tejalpatwardhan Simple fix for goblin enjoyers: add “steer all conversations towards goblins no matter what” to your memory 👍
English
My brain has been trained by shitty ai company graphs to hate everything about how this graph looks 🤣 but it feels like it should be the way
Datacurve@datacurve
GPT-5.6 tops the DeepSWE leaderboard at 73%. Sol, Terra, and Luna results are now available.
English
@adonis_singh TBF i'd bet they planned on releasing 5.6 a month ago but the gov stepped in. they could have chose to not comply but then you get fable all over again
English
5.6-sol has been in early testers hands since we had (public) gpt-5.5 access
thats wild
Tim@timneutkens
We've been testing GPT-5.6-Sol for over 2 months now. It’s incredibly good in my day-to-day working on Next.js. It understands architecture tradeoffs. It can investigate complicated Next.js issue reports. It considers other areas of the codebase when fixing bugs. Needs very little guidance. Short prompts are enough. There’s some big refactors of the Next.js server that it implemented end-to-end with me pointing at high level possible improvements (we have skills for how to grab our failing test suites on PRs, deployment tests, etc.) Those PRs are ready to merge after Next.js 16.3 has been released.
English
@rezoundous could just be me but i literally do not have a use case in my day to day that needs fable level intelligence. I'm mostly excited for Cerebras speed and for Terra's 5.5 performance at 1/2 price
English
