james

Typescript, Tanstack, Drizzle, NextJs, Vue3, Vite, React, Golang, Nativescript, Flutter, Nuxt3, OpenAi used by ChatGPT

[james @bcrap]

help team to use ai todo the tedious work:
1. image grouping
2. selecting best shot
3. matching with gps location based on time
4. matching shot to data
and entire harness to manage them, from previewing to manually validate, fix if needed. and custom prompting

[james @bcrap]

#ocode in action, can see it prevented the git stash from happening on auto mode

[james @bcrap]

all harmful git, web fetch, git revert are falling back to ask user for permission

[james @bcrap]

ocode automatic permission in action

[james @bcrap]

opensourcing https://t.co/fM1ABAoTLA #opencode alternative in golang
- advisor support
- automatic permission
- low memory usage, less than 50MB
- able to use chatgpt subscription, deepseek api, xiaomi coding plan, opencode go & zend api
- file explorer
- git explorer
- logs

[james @bcrap]

surprisingly on swe and swepro, deepseek v4 pro has higher benchmark compared to qwen3.7max

[james @bcrap]

for all open weights, we can see how capable are these models are. the lesser usage, normally means its higher agentic and coding capabilities. correct me if im wrong

[james @bcrap]

@damian_miranda @RaminNasibov XCOM 2 and 1

[james @bcrap]

@caps_raunak scary part is when u use the wrong model like deepseek v4 flash, it tend to make mistake and git revert those files silently if you put it on auto mode

[james @bcrap]

@socialwithaayan mempalace ate so much memory that I've disabled it

[james @bcrap]

@oracles yup, the company fires 10 thousands of people in the name of ai

[james @bcrap]

@elonmusk ya after doing some drama of firing most of the X staff in the past

[james @bcrap]

@VictorTaelin also im writing a opencode alternative in golang, havent release it yet

[james @bcrap]

@VictorTaelin ive added rules in my agents.md to specifically ask the agent to write to todo.md for anything thats deferred or not worked on for current session, it works wonderfully

[james @bcrap]

@VictorTaelin I started this when did a total conversion of a script from ts to golang and find it adding a alot of stub silently

[james @bcrap]

i just realised that #claude opus and sonnet code review will give generic non repo based review that does not adhere to agent rules including claude.md, but gpt 5.4 does a better job of understanding the repo and gives less false positive result

[james @bcrap]

@cjzafir benchmark?

[james @bcrap]

@coinbureau time to use other private cloud like megasync

[james @bcrap]

@sama make universal high income a reality world wide

[james @bcrap]

@perplexity_ai @Avast when?

[james @bcrap]

@kunchenguid i find the majority of American companies focus on all the completeness, like filling up all the gaps