I’ve heard that you get rapidly diminishing returns after ~100,000 tokens though. Has it been consistent in your experience?
GENERATIVE AI
-
Elon Musk proposes automatic proofreading and suggestions with Grok
By
–
We should automatically proofread and offer suggestions with Grok
-
HTTP Range Requests Optimize Large Model Weight Loading
By
–
I had the same question – looks to me like it's working around that limit by fetching 512MB slices of the model weights with HTTP range requests
-
System 1 and System 2 reasoning paths in AI models
By
–
Yeah, I think this is a possible path, system1 and system2. I already tried it with Gemini Live… and want to return to it some day.
-
Typeless AI Dictation Tool Review and Comparison
By
–
@typelessdotcomis amazing. I keep @WisprFlow when I need faster dictaction, but Typeless is definitely my new fave 🙂
-
Technological adoption brings ethical concerns about future regrets
By
–
Yeah, I'm one of them, but I remain deeply concerned that we are going to live to regret it!
-
OpenAI Codex Support for Your Development Work
By
–
Keep up the good work and do let us know if there’s other ways Codex/ OpenAI can help with your work!
-
Databricks Unveils Lakebase Operational Database for AI Agents
By
–
Databricks AI Days are underway, bringing together 15,000+ data and AI leaders to see how modern teams are building and shipping intelligent apps. This year, the spotlight is on Lakebase: a new category of operational database built for the age of agents, where storage and
-
Using AI for specification processing
By
–
Je pense que c'est très bien, c'est ce que je fais parfois pour faire mes specs et les filer à l'IA
-
Building Twitter Clone in 44 Minutes for $4 with Claude
By
–
Twitter started 20 years ago. In 2022 it was acquired for $44B. Today I build a clone of it in 44 minutes for $4 in Claude credits.