taf2

August 2025 for me but now days I’m much more extreme- it does it all max sol in mornings and then I do other things in the afternoon. I get more done than before with far less stress.

Would love to see the results if they had used /goal or similar

I'm not finding this on huggingface yet is and open model or is kimi now a closed model ?

Not finding anything about this while searching huggingface: https://huggingface.co/search/full-text?q=SWE-1.7 i assume this is another closed source model?

i love the built in AI - i created this tic tac toe game with an AI trash talking opponent -> https://taf2.github.io/ai-tic-tac-toe-trash-talk/

The timescale of this analysis is a big issue IMO- Covid hiring was all kinds of whacked out - with FANG companies competing to hire literally entire graduating cs classes.

this gives me children of time vibes

Best way to make your M series macbook pro feel like a good old fashion intel macbook pro. Run a local model.

when i read "keys" i figured "names" like in my .ssh/config a named host that i access with a key... but listening more it sounds like a new way to do networking over QUIC...

kill -9

I’m waiting to see results on deepswe - that benchmark really seemed accurate for opus and gpt 5.5…

I wanted to love flux.ai because i love codex... and if i could automate the creation of some PCB projects with as much success as I am with codex it would have been quiet fun in the shop... so i gave them a $100~ bucks and i got like nothing in return so I decided i'd wait and see... sounds like it has not improved.

That sucks I guess I won’t be using any Google llms anymore

are there any stats pointing to these students going to different schools? we know birth rates fell sharply starting ~2008 and have stayed low. [https://www.cdc.gov/nchs/data/vsrr/vsrr043.pdf]

4gb? Maybe on a raspberry pie it’s a problem - I’m sure there is a chrome flag to disable

What’s wrong with shipping a local llm? This is quite nice IMO is there a privacy concern with running it locally? I already have a few games I wrote web based using this and it’s quiet nice to not need a server to run my game in pure HTML from my file system

ok i picked a bad day to move from one register to another... i just spent the last hour frantically trying to figure out why the new register screwed us or the old register was screwing us...

i bet someone mentioned openclaw one too many times

Wow so like there are many services that rely on anthropics api.. if for example I inject the word openclaw into a bunch of chat bots or voice bots that might be using anthropics API would this also break them…

my goal was simple 2 sided pcbs, machined traces because i wanted to avoid chemical etching, but when it comes to via's chemicals are really the only way. The chemcials needed for plating via's are very toxic. my current thinking to avoid the really nasty ones is to try conductive ink (probably pretty bad too) but it maybe would work to coat the fr4 material and then allow a copper plating to take... really it's a fun process machining and laser the soldier mask.

In my journey to make pcb’s at home I decided to stop once I almost gassed myself and shifted instead to buying gpus

Just in time for ipv8 - https://www.ietf.org/archive/id/draft-thain-ipv8-00.html

I did this with qwen 3.5 - tool calling was the biggest issue but for getting it to work with vllm and mlx I just asked codex to help. The bulk of my the time was waiting on download. For vllm it created a proxy service to translate some codex idioms to vllm and vice versa. In practice I got good results on my first prompt but followup questions usually would fail due to the models trouble with tool calling - I need to try again with gemma4

I switched off claude when they nerfed opus 4.5 in August 2025, since then codex has clearly produced better code with fewer bugs. Opus 4.6 was more a temporary de-nerf of 4.5 but did not materially improve. codex has now a proven track record of producing stable results while introducing far fewer bugs.

I don't understand who's still using anthropic? The model produces more bugs and agrees to solutions that are clearly wrong at a much higher rate then codex. Codex produces significantly better code with fewer bugs and far less oversight. with /fast on codex it's not even slower then claude and consider it implements working code more reliably you have to use it less anyway. Beside anthropic appears to be more focused on fear mongering and other types of FUD and is a more closed solution I do not understand why so many people still appear to care what anthropic does and have not already moved on? </rant>

Bro Linux gaming is where it’s at - windoze is cooked

avoid bun is my take away... if anthropic decides you're a competitor and with the way AI is evolving you will be a competitor soon - don't rely on any anthropic tools or models.

I hope you are right

Yes exactly- one part I did not like is we have to also separately transcribe because it does not also provide what the person said only what the ai said

I forked and added tool calling by running another llm in parallel to infer when to call tools it works well for me to toggle lights on and off.

Code updates here https://github.com/taf2/personaplex