Currently sick asf
Doing some N=1 with Thymosin Alpha-1 to see if we can’t get over this cold before the weekend.
TA-1 has been something I’ve looked at researching for a while just never had a reason to. But this cold is kicking my ass. Will report back as I don’t think you can placebo your way out of a cold.
If you’re using Claude Code to build do the following and I promise the experience gets 10x better:
/model = Opus 5.5
/advisor = Fable 5.2
Then copy and paste the following into your session -
- Opus 5.5 runs the main session and edits the code
- search maps the repo on Haiku 5.5, read-only
- grep finds every call site on Haiku 5.5
- test-runner runs the suite on Haiku 5.5 and reports only failures
- Fable 5.2 on call as advisor, reads the full transcript when consulted
- JEV routes micro-forks in milliseconds
Rebuild my Claude Code setup around this tree:
1. Run the main session on Opus 5.5 with Fable 5.2 as advisor.
2. Create three read-only Haiku 5.5 subagents: search (maps the repo), grep (finds call sites), test-runner (runs the suite, reports only failures).
3. Add one rule to CLAUDE.md: consult the advisor before a plan locks, after the same error twice, and before a task is marked done.
4. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. Nothing gets edited until I say go.
Credit goes to @skunzu for creating the original write up on this! I just made it much shorter. Appreciate the setup Skunzu, my sessions are 10x better now!
Anthropic’s a for profit company. There goal is for you as a consumer to spend money on credits or at the very least their best membership.
It’s not about out promoting, it’s about prompting smarter but utilizing other models for tasks that they are perfectly efficient at before handing it back to the elite prompt to complete the task.
Bro is galavanting around like he wasn’t ILLEGALLY PRESCRIBING RETA to his own clients for the last year.
I guess Jesse is so smart that he forgot the internet is forever & there are A LOT of screenshots of his circulating on this app
Hopefully he enjoys the legal fees and the impact on his health.
Fckn clown
@Colasama I’ve used 2% of my weekly limit since switching 2 days ago, meanwhile 3 days ago I used my weekly limit and had to reset. This is why I went hunting for a solution.
The @ElyriaBio site has gone through some changes and the biggest additions are yet to come.
Expect credit cards and Apple Pay by the weekend. As well as pick a pack & weekly deals to both be live!
If you’re using Claude Code to build do the following and I promise the experience gets 10x better:
/model = Opus 5.5
/advisor = Fable 5.2
Then copy and paste the following into your session -
- Opus 5.5 runs the main session and edits the code
- search maps the repo on Haiku 5.5, read-only
- grep finds every call site on Haiku 5.5
- test-runner runs the suite on Haiku 5.5 and reports only failures
- Fable 5.2 on call as advisor, reads the full transcript when consulted
- JEV routes micro-forks in milliseconds
Rebuild my Claude Code setup around this tree:
1. Run the main session on Opus 5.5 with Fable 5.2 as advisor.
2. Create three read-only Haiku 5.5 subagents: search (maps the repo), grep (finds call sites), test-runner (runs the suite, reports only failures).
3. Add one rule to CLAUDE.md: consult the advisor before a plan locks, after the same error twice, and before a task is marked done.
4. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. Nothing gets edited until I say go.
Credit goes to @skunzu for creating the original write up on this! I just made it much shorter. Appreciate the setup Skunzu, my sessions are 10x better now!