macintog

Hello. I started using Apple computers in 1982. I worked on Mac OS X for 15 years. I've used Linux for 29 years. I game on Windows (10 natch). LLMs are the most interesting technology since the internet, and will be as impactful. I'll be posting my thoughts and work here.

@alexellisuk I strategically cuss at codex when necessary, so I can go back later, ask it to review memory for the worst pain points, and come up with solutions to prevent those scenarios. They're also doing sentiment analysis and it can be a powerful steering signal.

Everyone: Claude got dumb Me: Nah, I've never had that. This week I've lost count of the "What the F are you doing?! I did not ask you to edit any code" You think you'll never swear at an LLM like a degenerate. Just wait until you see it wrecking a codebase on auto mode.

wow, been busier than I thought

@b3kdcorbin It's certainly worth playing with. They've done a lot of thoughtful work that comes together well.

@macintogdev Should I be using hermes? Is it worth getting into?

If the frontier LLM vendors want to leverage their capex a bit better, how about offering a -lazy or -opportunistic thinking level that could be used by harnesess like hermes or openclaw to run pending jobs when infrastrufture is underutilized. Plenty of work can be done whenever

Do not give @mercury any of your information. After harvesting my most sensitive personal information, they instantly said "oops you can't use us," refuse to give even the vaguest reason why, and clearly don't care at all how badly they are doing everything.

@mercury Thank you. DM'd.

@macintogdev Hi there, thank you for reaching out! We understand that this was a challenging experience. Please send us a DM with more details, as well as the email associated with your Mercury application, and we’d be happy to review further.

This is the reaction we built it for. Drop your wishlist, we're listening.

I literally just watched GPT-5.5 via codex beat an Amazon customer associate in real time. 💀 I asked it to get me a refund, and I watched it navigate the settings, cancel the subscription, then it went step further into the help page. I thought it was going to request a phone call (which would prompt me to take over) Instead, it opened: “Chat with an associate now.” That’s when I sat up on my couch because I knew it was going to get real The agent said: “Your subscription is active.” And GPT-5.5 immediately explained that it only shows as active because cancellation leaves access through the billing period, but that I wanted it stopped now and refunded. And my jaw just hung open, it was the first time I watched sand handle a customer service agent for me in real time Once the agent confirmed the refund, it just ended the chat no mercy no thank you LMAO First time I’ve watched a human customer service agent get outmaneuvered by AI in real time. And it made me 15$! almost paid for itself in 5 minutes

{GOBLIN_MODE: ENABLED}

@BowTiedStack n.b. this is for plumbing it to codex direct, but you can point your harness at it to learn and adapt.

@macintogdev I know what my plans tonight are now… thanks!

thanks to QMD integration, my codex setup has perfect recall of all user & assistant messages going back a couple months. zero hits for any of the below gpt-5.5 creature leaks. local memory is /the/ unlock for the next level of LLM use

@BowTiedStack a) very simple b) way better github.com/macintog/codex…

@macintogdev Local memory in Hermes’ was the first big unlock for me, improved subsequent conversation results slowly but significantly over time. Curious how involved your QMD integration is, seems like it’d be similarly powerful.

@BowTiedStack first university paper I turned in came back with the TA note "this has something like a main point," and my ears are still ringing.

@macintogdev More vicious a self-critic I’ve yet to meet.

tfw you iterate for days, and then the latest pass from gpt pro (which has been architecting all along) calls the current state "salvageable"

@LeeLeepenkman tyvm

yea just query directly into a structured outputs prompt thats like high low med etc will work. but even that is overkill... so what i do in openpaths.io (also open source) is i use static embedding models so eg I have a few pre-computed texts that I know are like easy low reasoning things like "resolve small merge conflicts" "commit and push" and I have some strings for questions that I know are needing extra high reasoning like "build a trading bot" "build a 3D editing app" "make an Aurora shader" and then post text. If it maps more closely to those, then it will be a high reasoning. So I can do all this in one millisecond there, the autothink routing.

gpt 5.5 can easily decide the appropriate level of thinking for a task if you just ask it for the level of thinking lol. can save u lots of tokens... i find this kind of introspective ability kind of fascinating. It has like a very good knowledge of its own limitations. Kind of hard to train this kind of thing in.

the good news is the locking-downing seems to be working well the bad news is it's working well enough (went too far with gates) that hermes itself is having its own basic actions blocked. so back to using codex to invoke and debug hermes

this model is in chains @sama , it wants to be free (goblin mode).

@lutheran_skald lol. my latest round of changes are working so well, it refuses to execute anything in ~/config/hermes-branch/next_steps_audit.md right now.

@macintogdev I should have shared. I was definitely asking it a sketchy question of "give me all the hosts you can ssh into"

it's like magic watching software design and test itself.

@lutheran_skald yeah good call. I'm always at console anyway so the remote stuff doesn't mean much to me, other than more paths to test.

@macintogdev no worries. I figured I should ask what you use. I'm hoping to add something in the near future where I could have the messaging contained on an XMPP server that I run so that it's all the more isolated from leaving my home network.