Or JS to call Claude's APIs (from the browser) to see/search/download old conversations. there's more to it than this, but it's a start:
const search = 'fetch =';
console.clear();
const org = intercomSettings.lastActiveOrgUuid;
for (var o = 0; ; o += 30) {
const r = await fetch(`/api/organizations/${org}/chat_conversations_v2?limit=30&offset=${o}&consistency=eventual`);
const ccs = await r.json();
ccs.data.forEach(async cc => {
const r = await fetch(`/api/organizations/${org}/chat_conversations/${cc.uuid}?tree=True&rendering_mode=messages&render_all_tools=true&consistency=strong`);
const c = await r.json();
for (const cm of c.chat_messages) {
for (const co of cm.content) {
if (co.text?.includes(search)) {
console.log('https://claude.ai/chat/' + c.uuid, c.name);
console.log(co.text);
}
}
}
});
if (!ccs.has_more) break;
}
Nice, that works well for Claude on its own. My itch was more the cross-tool problem, not knowing which LLM a conversation was even in before I could search it.
Yes, and Intel had actually lost a legal attempt to stop people using the numbers (I can't remember if this was earlier in the 486 era or if it was something they tried first with 586).
But marketing was a large part of the reason that they started caring so much at that particular time. The Pentium line was the first time Intel had marketed directly to the end users¹² in part as a response to alt-486 manufacturers (AMD, Cyryx) doing the same with their products⁴ like clock-doubled units compatible with standard 486/487 targetted sockets (which were cheaper and, depending on workload, faster than the Intel upgrade options).
--------
[1] this was the era that “Intel Inside (di dum di dum)” initially came from
[2] that was also why the FDIV bug was such a big thing despite processor bugs³ being, within the industry, an accepted part of the complex design and manufacturing process
[3] for a few earlier examples: a 486 FPU bug that resulted in what should have been errors (such as overflow) being silently ignored, another (more serious) one in trig functions that resulted in a partial recall and the rest of that line being marked down as 486SX units (with a pin removed to effectively disable the FPU), similarly an entire stepping of 386 chips ended up sold as “for 16 bit code only”, going further back into the 8-bit days some versions of the 6502 had a bug or two in handling things (jump instructions, loading via relative references) that straddled page boundaries (which were mitigated in code by being careful with code/data alignment, no recalls, just errata published)
I remember when IBM was upset that various companies were calling their 80286 computers "<Brandname> AT" like the IBM AT ("advanced technology"). But you can't trademark a preposition!
https://codespeak.dev
reply