@danmana

Full stack software developer. When I'm not working I enjoy traveling around the world. Sometimes I do both :)

Cluj, Romania
Joined June 2009
My Jev maze solving experiments are not going well Poor guy is more lost than the guy from Memento without his tattoos and polaroids 🙈
57
Can Jev play poker? Yes Can Jev beat OpenAI? Maybe Here is a tournament between Jev, Terra and Astra
1
1
1
193
Here's another longer tournament with all models: Jev, Luna, Terra, Sol, Astra Overall I think Terra and Astra have the best play styles
1
1
44
All models get the same information: game rules, other player actions and chip count, pot size and the cards on the table. GPT models have thinking none/low to match Jev Jev and Luna are most cost effective
36
Is anyone else seeing a lot of Chinese characters in Opus 5 output lately? "The Chinese characters 描述 (miáoshù) mean “description” or “to describe.”"
23
Here is Jev from @typesafeai classifying 300 full chat sessions from our custom @vercel eve agent by failure reason. 323 sessions, 2M tokens done in 14s and costing $0.08 nitter.cf/CompleteSkeptic/status…
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
2
1
2
179
Downloading the full session logs from vercel takes 10x longer than classifying them with Jev 🤯
1
37
Bonus use-case for Jev - redacting PII information (inefficiently 🙈)
Here is Jev from @typesafeai classifying 300 full chat sessions from our custom @vercel eve agent by failure reason. 323 sessions, 2M tokens done in 14s and costing $0.08 nitter.cf/CompleteSkeptic/status…
50
If this style of Bash edits is driving you crazy in claude code, add this in .claude/settings.json { "env": { "CLAUDE_CODE_THRIFTY_SONIC": "0" } }
1
47
Apparently while in Auto Mode claude code adds this instruction. It drove me crazy that I couldn't read the diffs. And it also breaks /rewind
1
17
You don't need a network admin if you have Claude code. Traced a bad wifi connection at the office down to a faulty wire between the Gateway and PoE+ injector
1
47
It wasn't something I couldn't do on my own (probably faster but less accurately measured), but it was a nice test of Fable's logic and capabilities
1
14
My bad for the terrible screenshot quality - tried to screenshot it from my phone while out at lunch Here's a better one :)
14
Does ChatGPT always have to start its answers with Yes?
1
27
I mean if you can't just say so
13
First experiments with Astra compared with Fable 5.1. Initial results look good, but not quite Fable level. Same prompt, two interactive voxel worlds of Piața Unirii in Cluj-Napoca. Prompt adapted from @petergostev: Rome → Union Square in Cluj-Napoca. A few differences below.
2
1
3
397
My takeaway from these two runs: Astra gets some spatial facts more right, but feels more procedural; Fable captures more of the character and life of Piața Unirii. Both make lovely little worlds. I enjoyed the sunset views, especially Fable - feels warmer. Try the demos: piata-unirii.vercel.app
1
72
Finally, speed and costs (xhigh) Fable 5.1: 1h20m · $33.60 4.3K in / 347K out Cache: 23.9M read / 623K write Astra: 36m · ~$7.01* (estimate) 117.8K in / 61.1K out Cache: 2.776M read / 0? write Videos recorded by Astra. Code and prompt: github.com/danmana/piata-uni…
27